add sft model

README.md

@@ -1,3 +0,0 @@
----
-license: apache-2.0
----

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6375684142112732,
+    "eval_runtime": 168.7291,
+    "eval_samples_per_second": 30.807,
+    "eval_steps_per_second": 3.852,
+    "total_flos": 391576352194560.0,
+    "train_loss": 0.44177393167463547,
+    "train_runtime": 22000.6442,
+    "train_samples_per_second": 6.378,
+    "train_steps_per_second": 0.1
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "/mnt/bn/tokendance/models/Meta-Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "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-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6375684142112732,
+    "eval_runtime": 168.7291,
+    "eval_samples_per_second": 30.807,
+    "eval_steps_per_second": 3.852
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f72253e698a243edbcffcd68b95f4bd212735269f0ffb0430715925394713e5
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a40ac403b95f59a713937e69dd9366ba901efc1332fde0f176713a571c00e047
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d46d2cf7387d2e2a065b560aecf3ee8239721540581454f97b6184b9b69ac83d
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32a1c850c414369ff2197aa18e66bab005345dacb63d49ca3c1ec30535e949a3
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "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-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-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-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-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-00004-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-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-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-00001-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-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 391576352194560.0,
+    "train_loss": 0.44177393167463547,
+    "train_runtime": 22000.6442,
+    "train_samples_per_second": 6.378,
+    "train_steps_per_second": 0.1
+}

trainer_log.jsonl

@@ -0,0 +1,230 @@
+{"current_steps": 10, "total_steps": 2193, "loss": 0.9255, "learning_rate": 4.5454545454545457e-07, "epoch": 0.013679890560875513, "percentage": 0.46, "elapsed_time": "0:01:33", "remaining_time": "5:39:03"}
+{"current_steps": 20, "total_steps": 2193, "loss": 0.863, "learning_rate": 9.090909090909091e-07, "epoch": 0.027359781121751026, "percentage": 0.91, "elapsed_time": "0:03:00", "remaining_time": "5:26:44"}
+{"current_steps": 30, "total_steps": 2193, "loss": 0.7599, "learning_rate": 1.3636363636363636e-06, "epoch": 0.04103967168262654, "percentage": 1.37, "elapsed_time": "0:04:42", "remaining_time": "5:39:52"}
+{"current_steps": 40, "total_steps": 2193, "loss": 0.7184, "learning_rate": 1.8181818181818183e-06, "epoch": 0.05471956224350205, "percentage": 1.82, "elapsed_time": "0:06:08", "remaining_time": "5:30:18"}
+{"current_steps": 50, "total_steps": 2193, "loss": 0.6981, "learning_rate": 2.2727272727272728e-06, "epoch": 0.06839945280437756, "percentage": 2.28, "elapsed_time": "0:07:38", "remaining_time": "5:27:23"}
+{"current_steps": 60, "total_steps": 2193, "loss": 0.6943, "learning_rate": 2.7272727272727272e-06, "epoch": 0.08207934336525308, "percentage": 2.74, "elapsed_time": "0:09:12", "remaining_time": "5:27:29"}
+{"current_steps": 70, "total_steps": 2193, "loss": 0.6687, "learning_rate": 3.181818181818182e-06, "epoch": 0.09575923392612859, "percentage": 3.19, "elapsed_time": "0:10:48", "remaining_time": "5:27:44"}
+{"current_steps": 80, "total_steps": 2193, "loss": 0.6694, "learning_rate": 3.6363636363636366e-06, "epoch": 0.1094391244870041, "percentage": 3.65, "elapsed_time": "0:12:25", "remaining_time": "5:28:01"}
+{"current_steps": 90, "total_steps": 2193, "loss": 0.6602, "learning_rate": 4.0909090909090915e-06, "epoch": 0.12311901504787962, "percentage": 4.1, "elapsed_time": "0:14:02", "remaining_time": "5:28:17"}
+{"current_steps": 100, "total_steps": 2193, "loss": 0.6514, "learning_rate": 4.5454545454545455e-06, "epoch": 0.13679890560875513, "percentage": 4.56, "elapsed_time": "0:15:30", "remaining_time": "5:24:34"}
+{"current_steps": 110, "total_steps": 2193, "loss": 0.6413, "learning_rate": 5e-06, "epoch": 0.15047879616963064, "percentage": 5.02, "elapsed_time": "0:17:01", "remaining_time": "5:22:16"}
+{"current_steps": 120, "total_steps": 2193, "loss": 0.6584, "learning_rate": 5.4545454545454545e-06, "epoch": 0.16415868673050615, "percentage": 5.47, "elapsed_time": "0:18:22", "remaining_time": "5:17:30"}
+{"current_steps": 130, "total_steps": 2193, "loss": 0.6292, "learning_rate": 5.90909090909091e-06, "epoch": 0.17783857729138167, "percentage": 5.93, "elapsed_time": "0:19:51", "remaining_time": "5:15:06"}
+{"current_steps": 140, "total_steps": 2193, "loss": 0.6487, "learning_rate": 6.363636363636364e-06, "epoch": 0.19151846785225718, "percentage": 6.38, "elapsed_time": "0:21:21", "remaining_time": "5:13:12"}
+{"current_steps": 150, "total_steps": 2193, "loss": 0.6294, "learning_rate": 6.818181818181818e-06, "epoch": 0.2051983584131327, "percentage": 6.84, "elapsed_time": "0:22:48", "remaining_time": "5:10:45"}
+{"current_steps": 160, "total_steps": 2193, "loss": 0.6443, "learning_rate": 7.272727272727273e-06, "epoch": 0.2188782489740082, "percentage": 7.3, "elapsed_time": "0:24:20", "remaining_time": "5:09:19"}
+{"current_steps": 170, "total_steps": 2193, "loss": 0.6411, "learning_rate": 7.727272727272727e-06, "epoch": 0.23255813953488372, "percentage": 7.75, "elapsed_time": "0:25:49", "remaining_time": "5:07:23"}
+{"current_steps": 180, "total_steps": 2193, "loss": 0.6385, "learning_rate": 8.181818181818183e-06, "epoch": 0.24623803009575923, "percentage": 8.21, "elapsed_time": "0:27:18", "remaining_time": "5:05:28"}
+{"current_steps": 190, "total_steps": 2193, "loss": 0.6466, "learning_rate": 8.636363636363637e-06, "epoch": 0.25991792065663477, "percentage": 8.66, "elapsed_time": "0:28:56", "remaining_time": "5:05:01"}
+{"current_steps": 200, "total_steps": 2193, "loss": 0.6185, "learning_rate": 9.090909090909091e-06, "epoch": 0.27359781121751026, "percentage": 9.12, "elapsed_time": "0:30:19", "remaining_time": "5:02:08"}
+{"current_steps": 200, "total_steps": 2193, "eval_loss": 0.6430878043174744, "epoch": 0.27359781121751026, "percentage": 9.12, "elapsed_time": "0:33:07", "remaining_time": "5:30:08"}
+{"current_steps": 210, "total_steps": 2193, "loss": 0.6235, "learning_rate": 9.545454545454547e-06, "epoch": 0.2872777017783858, "percentage": 9.58, "elapsed_time": "0:34:43", "remaining_time": "5:27:50"}
+{"current_steps": 220, "total_steps": 2193, "loss": 0.6305, "learning_rate": 1e-05, "epoch": 0.3009575923392613, "percentage": 10.03, "elapsed_time": "0:36:08", "remaining_time": "5:24:08"}
+{"current_steps": 230, "total_steps": 2193, "loss": 0.6308, "learning_rate": 9.99936616472178e-06, "epoch": 0.3146374829001368, "percentage": 10.49, "elapsed_time": "0:37:42", "remaining_time": "5:21:49"}
+{"current_steps": 240, "total_steps": 2193, "loss": 0.6331, "learning_rate": 9.997464819585985e-06, "epoch": 0.3283173734610123, "percentage": 10.94, "elapsed_time": "0:39:04", "remaining_time": "5:17:54"}
+{"current_steps": 250, "total_steps": 2193, "loss": 0.6319, "learning_rate": 9.994296446648463e-06, "epoch": 0.34199726402188785, "percentage": 11.4, "elapsed_time": "0:40:37", "remaining_time": "5:15:45"}
+{"current_steps": 260, "total_steps": 2193, "loss": 0.6368, "learning_rate": 9.989861849199833e-06, "epoch": 0.35567715458276333, "percentage": 11.86, "elapsed_time": "0:42:11", "remaining_time": "5:13:39"}
+{"current_steps": 270, "total_steps": 2193, "loss": 0.628, "learning_rate": 9.984162151561814e-06, "epoch": 0.3693570451436389, "percentage": 12.31, "elapsed_time": "0:43:40", "remaining_time": "5:11:02"}
+{"current_steps": 280, "total_steps": 2193, "loss": 0.6191, "learning_rate": 9.977198798802186e-06, "epoch": 0.38303693570451436, "percentage": 12.77, "elapsed_time": "0:45:06", "remaining_time": "5:08:09"}
+{"current_steps": 290, "total_steps": 2193, "loss": 0.6311, "learning_rate": 9.9689735563684e-06, "epoch": 0.3967168262653899, "percentage": 13.22, "elapsed_time": "0:46:43", "remaining_time": "5:06:33"}
+{"current_steps": 300, "total_steps": 2193, "loss": 0.6204, "learning_rate": 9.959488509639986e-06, "epoch": 0.4103967168262654, "percentage": 13.68, "elapsed_time": "0:48:27", "remaining_time": "5:05:48"}
+{"current_steps": 310, "total_steps": 2193, "loss": 0.6185, "learning_rate": 9.948746063399836e-06, "epoch": 0.4240766073871409, "percentage": 14.14, "elapsed_time": "0:49:56", "remaining_time": "5:03:21"}
+{"current_steps": 320, "total_steps": 2193, "loss": 0.63, "learning_rate": 9.936748941224514e-06, "epoch": 0.4377564979480164, "percentage": 14.59, "elapsed_time": "0:51:25", "remaining_time": "5:00:57"}
+{"current_steps": 330, "total_steps": 2193, "loss": 0.6325, "learning_rate": 9.923500184793728e-06, "epoch": 0.45143638850889195, "percentage": 15.05, "elapsed_time": "0:52:57", "remaining_time": "4:58:56"}
+{"current_steps": 340, "total_steps": 2193, "loss": 0.6202, "learning_rate": 9.909003153119165e-06, "epoch": 0.46511627906976744, "percentage": 15.5, "elapsed_time": "0:54:29", "remaining_time": "4:57:01"}
+{"current_steps": 350, "total_steps": 2193, "loss": 0.6157, "learning_rate": 9.893261521692865e-06, "epoch": 0.478796169630643, "percentage": 15.96, "elapsed_time": "0:56:02", "remaining_time": "4:55:07"}
+{"current_steps": 360, "total_steps": 2193, "loss": 0.6244, "learning_rate": 9.876279281555363e-06, "epoch": 0.49247606019151846, "percentage": 16.42, "elapsed_time": "0:57:30", "remaining_time": "4:52:49"}
+{"current_steps": 370, "total_steps": 2193, "loss": 0.6209, "learning_rate": 9.858060738283819e-06, "epoch": 0.506155950752394, "percentage": 16.87, "elapsed_time": "0:58:59", "remaining_time": "4:50:40"}
+{"current_steps": 380, "total_steps": 2193, "loss": 0.6168, "learning_rate": 9.838610510900412e-06, "epoch": 0.5198358413132695, "percentage": 17.33, "elapsed_time": "1:00:25", "remaining_time": "4:48:16"}
+{"current_steps": 390, "total_steps": 2193, "loss": 0.6273, "learning_rate": 9.817933530701258e-06, "epoch": 0.533515731874145, "percentage": 17.78, "elapsed_time": "1:02:02", "remaining_time": "4:46:48"}
+{"current_steps": 400, "total_steps": 2193, "loss": 0.6088, "learning_rate": 9.79603504000615e-06, "epoch": 0.5471956224350205, "percentage": 18.24, "elapsed_time": "1:03:33", "remaining_time": "4:44:54"}
+{"current_steps": 400, "total_steps": 2193, "eval_loss": 0.6271325945854187, "epoch": 0.5471956224350205, "percentage": 18.24, "elapsed_time": "1:06:21", "remaining_time": "4:57:26"}
+{"current_steps": 410, "total_steps": 2193, "loss": 0.6137, "learning_rate": 9.772920590829471e-06, "epoch": 0.560875512995896, "percentage": 18.7, "elapsed_time": "1:08:00", "remaining_time": "4:55:46"}
+{"current_steps": 420, "total_steps": 2193, "loss": 0.6143, "learning_rate": 9.748596043472547e-06, "epoch": 0.5745554035567716, "percentage": 19.15, "elapsed_time": "1:09:34", "remaining_time": "4:53:44"}
+{"current_steps": 430, "total_steps": 2193, "loss": 0.6068, "learning_rate": 9.723067565037874e-06, "epoch": 0.5882352941176471, "percentage": 19.61, "elapsed_time": "1:11:15", "remaining_time": "4:52:10"}
+{"current_steps": 440, "total_steps": 2193, "loss": 0.6263, "learning_rate": 9.696341627865548e-06, "epoch": 0.6019151846785226, "percentage": 20.06, "elapsed_time": "1:12:40", "remaining_time": "4:49:31"}
+{"current_steps": 450, "total_steps": 2193, "loss": 0.624, "learning_rate": 9.668425007892298e-06, "epoch": 0.615595075239398, "percentage": 20.52, "elapsed_time": "1:14:16", "remaining_time": "4:47:42"}
+{"current_steps": 460, "total_steps": 2193, "loss": 0.6115, "learning_rate": 9.639324782933556e-06, "epoch": 0.6292749658002736, "percentage": 20.98, "elapsed_time": "1:15:44", "remaining_time": "4:45:21"}
+{"current_steps": 470, "total_steps": 2193, "loss": 0.6231, "learning_rate": 9.609048330888996e-06, "epoch": 0.6429548563611491, "percentage": 21.43, "elapsed_time": "1:17:17", "remaining_time": "4:43:20"}
+{"current_steps": 480, "total_steps": 2193, "loss": 0.6087, "learning_rate": 9.577603327871983e-06, "epoch": 0.6566347469220246, "percentage": 21.89, "elapsed_time": "1:18:47", "remaining_time": "4:41:12"}
+{"current_steps": 490, "total_steps": 2193, "loss": 0.6207, "learning_rate": 9.544997746263409e-06, "epoch": 0.6703146374829001, "percentage": 22.34, "elapsed_time": "1:20:16", "remaining_time": "4:38:58"}
+{"current_steps": 500, "total_steps": 2193, "loss": 0.5912, "learning_rate": 9.511239852690429e-06, "epoch": 0.6839945280437757, "percentage": 22.8, "elapsed_time": "1:21:54", "remaining_time": "4:37:20"}
+{"current_steps": 510, "total_steps": 2193, "loss": 0.6084, "learning_rate": 9.476338205930593e-06, "epoch": 0.6976744186046512, "percentage": 23.26, "elapsed_time": "1:23:39", "remaining_time": "4:36:04"}
+{"current_steps": 520, "total_steps": 2193, "loss": 0.6132, "learning_rate": 9.440301654741889e-06, "epoch": 0.7113543091655267, "percentage": 23.71, "elapsed_time": "1:25:10", "remaining_time": "4:34:00"}
+{"current_steps": 530, "total_steps": 2193, "loss": 0.6194, "learning_rate": 9.403139335619302e-06, "epoch": 0.7250341997264022, "percentage": 24.17, "elapsed_time": "1:26:42", "remaining_time": "4:32:05"}
+{"current_steps": 540, "total_steps": 2193, "loss": 0.5951, "learning_rate": 9.36486067047838e-06, "epoch": 0.7387140902872777, "percentage": 24.62, "elapsed_time": "1:28:14", "remaining_time": "4:30:08"}
+{"current_steps": 550, "total_steps": 2193, "loss": 0.6007, "learning_rate": 9.325475364266474e-06, "epoch": 0.7523939808481532, "percentage": 25.08, "elapsed_time": "1:29:44", "remaining_time": "4:28:03"}
+{"current_steps": 560, "total_steps": 2193, "loss": 0.6146, "learning_rate": 9.28499340250219e-06, "epoch": 0.7660738714090287, "percentage": 25.54, "elapsed_time": "1:31:10", "remaining_time": "4:25:50"}
+{"current_steps": 570, "total_steps": 2193, "loss": 0.6077, "learning_rate": 9.24342504874373e-06, "epoch": 0.7797537619699042, "percentage": 25.99, "elapsed_time": "1:32:51", "remaining_time": "4:24:25"}
+{"current_steps": 580, "total_steps": 2193, "loss": 0.6001, "learning_rate": 9.200780841986717e-06, "epoch": 0.7934336525307798, "percentage": 26.45, "elapsed_time": "1:34:26", "remaining_time": "4:22:38"}
+{"current_steps": 590, "total_steps": 2193, "loss": 0.6289, "learning_rate": 9.157071593992217e-06, "epoch": 0.8071135430916553, "percentage": 26.9, "elapsed_time": "1:35:59", "remaining_time": "4:20:49"}
+{"current_steps": 600, "total_steps": 2193, "loss": 0.6083, "learning_rate": 9.112308386545574e-06, "epoch": 0.8207934336525308, "percentage": 27.36, "elapsed_time": "1:37:29", "remaining_time": "4:18:49"}
+{"current_steps": 600, "total_steps": 2193, "eval_loss": 0.6138648390769958, "epoch": 0.8207934336525308, "percentage": 27.36, "elapsed_time": "1:40:18", "remaining_time": "4:26:17"}
+{"current_steps": 610, "total_steps": 2193, "loss": 0.6028, "learning_rate": 9.066502568646805e-06, "epoch": 0.8344733242134063, "percentage": 27.82, "elapsed_time": "1:41:58", "remaining_time": "4:24:37"}
+{"current_steps": 620, "total_steps": 2193, "loss": 0.6025, "learning_rate": 9.019665753633247e-06, "epoch": 0.8481532147742818, "percentage": 28.27, "elapsed_time": "1:43:20", "remaining_time": "4:22:12"}
+{"current_steps": 630, "total_steps": 2193, "loss": 0.6072, "learning_rate": 8.971809816235164e-06, "epoch": 0.8618331053351573, "percentage": 28.73, "elapsed_time": "1:44:56", "remaining_time": "4:20:22"}
+{"current_steps": 640, "total_steps": 2193, "loss": 0.6014, "learning_rate": 8.922946889565119e-06, "epoch": 0.8755129958960328, "percentage": 29.18, "elapsed_time": "1:46:21", "remaining_time": "4:18:06"}
+{"current_steps": 650, "total_steps": 2193, "loss": 0.584, "learning_rate": 8.873089362041797e-06, "epoch": 0.8891928864569083, "percentage": 29.64, "elapsed_time": "1:47:57", "remaining_time": "4:16:16"}
+{"current_steps": 660, "total_steps": 2193, "loss": 0.5929, "learning_rate": 8.822249874249131e-06, "epoch": 0.9028727770177839, "percentage": 30.1, "elapsed_time": "1:49:31", "remaining_time": "4:14:24"}
+{"current_steps": 670, "total_steps": 2193, "loss": 0.5954, "learning_rate": 8.770441315731477e-06, "epoch": 0.9165526675786594, "percentage": 30.55, "elapsed_time": "1:51:03", "remaining_time": "4:12:26"}
+{"current_steps": 680, "total_steps": 2193, "loss": 0.5876, "learning_rate": 8.717676821725679e-06, "epoch": 0.9302325581395349, "percentage": 31.01, "elapsed_time": "1:52:31", "remaining_time": "4:10:21"}
+{"current_steps": 690, "total_steps": 2193, "loss": 0.6006, "learning_rate": 8.663969769830824e-06, "epoch": 0.9439124487004104, "percentage": 31.46, "elapsed_time": "1:53:52", "remaining_time": "4:08:03"}
+{"current_steps": 700, "total_steps": 2193, "loss": 0.5974, "learning_rate": 8.609333776616592e-06, "epoch": 0.957592339261286, "percentage": 31.92, "elapsed_time": "1:55:30", "remaining_time": "4:06:21"}
+{"current_steps": 710, "total_steps": 2193, "loss": 0.6043, "learning_rate": 8.553782694170963e-06, "epoch": 0.9712722298221614, "percentage": 32.38, "elapsed_time": "1:57:04", "remaining_time": "4:04:32"}
+{"current_steps": 720, "total_steps": 2193, "loss": 0.5779, "learning_rate": 8.497330606588257e-06, "epoch": 0.9849521203830369, "percentage": 32.83, "elapsed_time": "1:58:37", "remaining_time": "4:02:41"}
+{"current_steps": 730, "total_steps": 2193, "loss": 0.6108, "learning_rate": 8.439991826398331e-06, "epoch": 0.9986320109439124, "percentage": 33.29, "elapsed_time": "2:00:09", "remaining_time": "4:00:49"}
+{"current_steps": 740, "total_steps": 2193, "loss": 0.4662, "learning_rate": 8.38178089093786e-06, "epoch": 1.012311901504788, "percentage": 33.74, "elapsed_time": "2:01:40", "remaining_time": "3:58:55"}
+{"current_steps": 750, "total_steps": 2193, "loss": 0.4296, "learning_rate": 8.322712558664635e-06, "epoch": 1.0259917920656634, "percentage": 34.2, "elapsed_time": "2:03:09", "remaining_time": "3:56:58"}
+{"current_steps": 760, "total_steps": 2193, "loss": 0.4295, "learning_rate": 8.262801805415783e-06, "epoch": 1.039671682626539, "percentage": 34.66, "elapsed_time": "2:04:40", "remaining_time": "3:55:04"}
+{"current_steps": 770, "total_steps": 2193, "loss": 0.4244, "learning_rate": 8.202063820610887e-06, "epoch": 1.0533515731874146, "percentage": 35.11, "elapsed_time": "2:06:11", "remaining_time": "3:53:11"}
+{"current_steps": 780, "total_steps": 2193, "loss": 0.4257, "learning_rate": 8.140514003400945e-06, "epoch": 1.06703146374829, "percentage": 35.57, "elapsed_time": "2:07:46", "remaining_time": "3:51:27"}
+{"current_steps": 790, "total_steps": 2193, "loss": 0.4325, "learning_rate": 8.078167958764162e-06, "epoch": 1.0807113543091655, "percentage": 36.02, "elapsed_time": "2:09:20", "remaining_time": "3:49:42"}
+{"current_steps": 800, "total_steps": 2193, "loss": 0.4314, "learning_rate": 8.015041493549562e-06, "epoch": 1.094391244870041, "percentage": 36.48, "elapsed_time": "2:10:45", "remaining_time": "3:47:41"}
+{"current_steps": 800, "total_steps": 2193, "eval_loss": 0.6188511848449707, "epoch": 1.094391244870041, "percentage": 36.48, "elapsed_time": "2:13:34", "remaining_time": "3:52:34"}
+{"current_steps": 810, "total_steps": 2193, "loss": 0.4335, "learning_rate": 7.951150612469396e-06, "epoch": 1.1080711354309165, "percentage": 36.94, "elapsed_time": "2:15:02", "remaining_time": "3:50:34"}
+{"current_steps": 820, "total_steps": 2193, "loss": 0.4271, "learning_rate": 7.886511514041422e-06, "epoch": 1.121751025991792, "percentage": 37.39, "elapsed_time": "2:16:28", "remaining_time": "3:48:30"}
+{"current_steps": 830, "total_steps": 2193, "loss": 0.4367, "learning_rate": 7.821140586482013e-06, "epoch": 1.1354309165526675, "percentage": 37.85, "elapsed_time": "2:18:02", "remaining_time": "3:46:41"}
+{"current_steps": 840, "total_steps": 2193, "loss": 0.4359, "learning_rate": 7.755054403551191e-06, "epoch": 1.1491108071135432, "percentage": 38.3, "elapsed_time": "2:19:38", "remaining_time": "3:44:55"}
+{"current_steps": 850, "total_steps": 2193, "loss": 0.433, "learning_rate": 7.688269720350616e-06, "epoch": 1.1627906976744187, "percentage": 38.76, "elapsed_time": "2:21:12", "remaining_time": "3:43:05"}
+{"current_steps": 860, "total_steps": 2193, "loss": 0.4387, "learning_rate": 7.620803469075588e-06, "epoch": 1.1764705882352942, "percentage": 39.22, "elapsed_time": "2:22:37", "remaining_time": "3:41:04"}
+{"current_steps": 870, "total_steps": 2193, "loss": 0.4198, "learning_rate": 7.552672754722169e-06, "epoch": 1.1901504787961696, "percentage": 39.67, "elapsed_time": "2:24:06", "remaining_time": "3:39:08"}
+{"current_steps": 880, "total_steps": 2193, "loss": 0.4356, "learning_rate": 7.483894850750473e-06, "epoch": 1.2038303693570451, "percentage": 40.13, "elapsed_time": "2:25:38", "remaining_time": "3:37:18"}
+{"current_steps": 890, "total_steps": 2193, "loss": 0.4334, "learning_rate": 7.414487194705258e-06, "epoch": 1.2175102599179206, "percentage": 40.58, "elapsed_time": "2:27:07", "remaining_time": "3:35:23"}
+{"current_steps": 900, "total_steps": 2193, "loss": 0.4335, "learning_rate": 7.344467383794917e-06, "epoch": 1.231190150478796, "percentage": 41.04, "elapsed_time": "2:28:35", "remaining_time": "3:33:28"}
+{"current_steps": 910, "total_steps": 2193, "loss": 0.4338, "learning_rate": 7.2738531704299845e-06, "epoch": 1.2448700410396718, "percentage": 41.5, "elapsed_time": "2:30:05", "remaining_time": "3:31:36"}
+{"current_steps": 920, "total_steps": 2193, "loss": 0.4506, "learning_rate": 7.2026624577222855e-06, "epoch": 1.2585499316005473, "percentage": 41.95, "elapsed_time": "2:31:34", "remaining_time": "3:29:44"}
+{"current_steps": 930, "total_steps": 2193, "loss": 0.4356, "learning_rate": 7.1309132949459e-06, "epoch": 1.2722298221614228, "percentage": 42.41, "elapsed_time": "2:33:09", "remaining_time": "3:28:00"}
+{"current_steps": 940, "total_steps": 2193, "loss": 0.4293, "learning_rate": 7.058623872961051e-06, "epoch": 1.2859097127222983, "percentage": 42.86, "elapsed_time": "2:34:33", "remaining_time": "3:26:01"}
+{"current_steps": 950, "total_steps": 2193, "loss": 0.4268, "learning_rate": 6.985812519602094e-06, "epoch": 1.2995896032831737, "percentage": 43.32, "elapsed_time": "2:35:59", "remaining_time": "3:24:06"}
+{"current_steps": 960, "total_steps": 2193, "loss": 0.4286, "learning_rate": 6.912497695030796e-06, "epoch": 1.3132694938440492, "percentage": 43.78, "elapsed_time": "2:37:35", "remaining_time": "3:22:24"}
+{"current_steps": 970, "total_steps": 2193, "loss": 0.4313, "learning_rate": 6.838697987056046e-06, "epoch": 1.3269493844049247, "percentage": 44.23, "elapsed_time": "2:38:58", "remaining_time": "3:20:25"}
+{"current_steps": 980, "total_steps": 2193, "loss": 0.4279, "learning_rate": 6.764432106421223e-06, "epoch": 1.3406292749658002, "percentage": 44.69, "elapsed_time": "2:40:25", "remaining_time": "3:18:33"}
+{"current_steps": 990, "total_steps": 2193, "loss": 0.4305, "learning_rate": 6.68971888206037e-06, "epoch": 1.3543091655266757, "percentage": 45.14, "elapsed_time": "2:41:56", "remaining_time": "3:16:46"}
+{"current_steps": 1000, "total_steps": 2193, "loss": 0.4322, "learning_rate": 6.614577256324426e-06, "epoch": 1.3679890560875512, "percentage": 45.6, "elapsed_time": "2:43:24", "remaining_time": "3:14:56"}
+{"current_steps": 1000, "total_steps": 2193, "eval_loss": 0.617301881313324, "epoch": 1.3679890560875512, "percentage": 45.6, "elapsed_time": "2:46:12", "remaining_time": "3:18:17"}
+{"current_steps": 1010, "total_steps": 2193, "loss": 0.4279, "learning_rate": 6.539026280178695e-06, "epoch": 1.3816689466484269, "percentage": 46.06, "elapsed_time": "2:49:25", "remaining_time": "3:18:26"}
+{"current_steps": 1020, "total_steps": 2193, "loss": 0.4309, "learning_rate": 6.46308510837277e-06, "epoch": 1.3953488372093024, "percentage": 46.51, "elapsed_time": "2:50:43", "remaining_time": "3:16:20"}
+{"current_steps": 1030, "total_steps": 2193, "loss": 0.4349, "learning_rate": 6.386772994584156e-06, "epoch": 1.4090287277701778, "percentage": 46.97, "elapsed_time": "2:52:22", "remaining_time": "3:14:37"}
+{"current_steps": 1040, "total_steps": 2193, "loss": 0.4232, "learning_rate": 6.310109286536801e-06, "epoch": 1.4227086183310533, "percentage": 47.42, "elapsed_time": "2:54:02", "remaining_time": "3:12:57"}
+{"current_steps": 1050, "total_steps": 2193, "loss": 0.4355, "learning_rate": 6.233113421095794e-06, "epoch": 1.4363885088919288, "percentage": 47.88, "elapsed_time": "2:55:43", "remaining_time": "3:11:17"}
+{"current_steps": 1060, "total_steps": 2193, "loss": 0.4286, "learning_rate": 6.155804919339453e-06, "epoch": 1.4500683994528043, "percentage": 48.34, "elapsed_time": "2:57:16", "remaining_time": "3:09:28"}
+{"current_steps": 1070, "total_steps": 2193, "loss": 0.4314, "learning_rate": 6.078203381610064e-06, "epoch": 1.46374829001368, "percentage": 48.79, "elapsed_time": "2:58:48", "remaining_time": "3:07:40"}
+{"current_steps": 1080, "total_steps": 2193, "loss": 0.4292, "learning_rate": 6.000328482544532e-06, "epoch": 1.4774281805745555, "percentage": 49.25, "elapsed_time": "3:00:20", "remaining_time": "3:05:50"}
+{"current_steps": 1090, "total_steps": 2193, "loss": 0.4295, "learning_rate": 5.92219996608618e-06, "epoch": 1.491108071135431, "percentage": 49.7, "elapsed_time": "3:01:48", "remaining_time": "3:03:59"}
+{"current_steps": 1100, "total_steps": 2193, "loss": 0.4399, "learning_rate": 5.843837640479e-06, "epoch": 1.5047879616963065, "percentage": 50.16, "elapsed_time": "3:03:17", "remaining_time": "3:02:07"}
+{"current_steps": 1110, "total_steps": 2193, "loss": 0.424, "learning_rate": 5.765261373245567e-06, "epoch": 1.518467852257182, "percentage": 50.62, "elapsed_time": "3:04:53", "remaining_time": "3:00:23"}
+{"current_steps": 1120, "total_steps": 2193, "loss": 0.4285, "learning_rate": 5.686491086149965e-06, "epoch": 1.5321477428180574, "percentage": 51.07, "elapsed_time": "3:06:36", "remaining_time": "2:58:46"}
+{"current_steps": 1130, "total_steps": 2193, "loss": 0.4397, "learning_rate": 5.60754675014693e-06, "epoch": 1.545827633378933, "percentage": 51.53, "elapsed_time": "3:08:20", "remaining_time": "2:57:10"}
+{"current_steps": 1140, "total_steps": 2193, "loss": 0.4184, "learning_rate": 5.528448380318532e-06, "epoch": 1.5595075239398084, "percentage": 51.98, "elapsed_time": "3:09:48", "remaining_time": "2:55:19"}
+{"current_steps": 1150, "total_steps": 2193, "loss": 0.4199, "learning_rate": 5.449216030799667e-06, "epoch": 1.573187414500684, "percentage": 52.44, "elapsed_time": "3:11:29", "remaining_time": "2:53:40"}
+{"current_steps": 1160, "total_steps": 2193, "loss": 0.4392, "learning_rate": 5.369869789693656e-06, "epoch": 1.5868673050615594, "percentage": 52.9, "elapsed_time": "3:12:55", "remaining_time": "2:51:47"}
+{"current_steps": 1170, "total_steps": 2193, "loss": 0.4337, "learning_rate": 5.290429773979224e-06, "epoch": 1.6005471956224349, "percentage": 53.35, "elapsed_time": "3:14:33", "remaining_time": "2:50:06"}
+{"current_steps": 1180, "total_steps": 2193, "loss": 0.4448, "learning_rate": 5.2109161244101545e-06, "epoch": 1.6142270861833106, "percentage": 53.81, "elapsed_time": "3:16:11", "remaining_time": "2:48:25"}
+{"current_steps": 1190, "total_steps": 2193, "loss": 0.4286, "learning_rate": 5.1313490004089265e-06, "epoch": 1.627906976744186, "percentage": 54.26, "elapsed_time": "3:17:33", "remaining_time": "2:46:31"}
+{"current_steps": 1200, "total_steps": 2193, "loss": 0.4368, "learning_rate": 5.05174857495561e-06, "epoch": 1.6415868673050615, "percentage": 54.72, "elapsed_time": "3:19:08", "remaining_time": "2:44:47"}
+{"current_steps": 1200, "total_steps": 2193, "eval_loss": 0.608180046081543, "epoch": 1.6415868673050615, "percentage": 54.72, "elapsed_time": "3:21:56", "remaining_time": "2:47:06"}
+{"current_steps": 1210, "total_steps": 2193, "loss": 0.4276, "learning_rate": 4.972135029473333e-06, "epoch": 1.655266757865937, "percentage": 55.18, "elapsed_time": "3:23:25", "remaining_time": "2:45:16"}
+{"current_steps": 1220, "total_steps": 2193, "loss": 0.4334, "learning_rate": 4.892528548711594e-06, "epoch": 1.6689466484268127, "percentage": 55.63, "elapsed_time": "3:24:52", "remaining_time": "2:43:23"}
+{"current_steps": 1230, "total_steps": 2193, "loss": 0.4272, "learning_rate": 4.812949315628746e-06, "epoch": 1.6826265389876882, "percentage": 56.09, "elapsed_time": "3:26:25", "remaining_time": "2:41:36"}
+{"current_steps": 1240, "total_steps": 2193, "loss": 0.4164, "learning_rate": 4.7334175062749275e-06, "epoch": 1.6963064295485637, "percentage": 56.54, "elapsed_time": "3:28:03", "remaining_time": "2:39:54"}
+{"current_steps": 1250, "total_steps": 2193, "loss": 0.4415, "learning_rate": 4.653953284676737e-06, "epoch": 1.7099863201094392, "percentage": 57.0, "elapsed_time": "3:29:36", "remaining_time": "2:38:07"}
+{"current_steps": 1260, "total_steps": 2193, "loss": 0.4161, "learning_rate": 4.574576797724984e-06, "epoch": 1.7236662106703147, "percentage": 57.46, "elapsed_time": "3:31:06", "remaining_time": "2:36:19"}
+{"current_steps": 1270, "total_steps": 2193, "loss": 0.4326, "learning_rate": 4.495308170066739e-06, "epoch": 1.7373461012311902, "percentage": 57.91, "elapsed_time": "3:32:36", "remaining_time": "2:34:30"}
+{"current_steps": 1280, "total_steps": 2193, "loss": 0.4426, "learning_rate": 4.4161674990030715e-06, "epoch": 1.7510259917920656, "percentage": 58.37, "elapsed_time": "3:34:17", "remaining_time": "2:32:51"}
+{"current_steps": 1290, "total_steps": 2193, "loss": 0.4263, "learning_rate": 4.3371748493936834e-06, "epoch": 1.7647058823529411, "percentage": 58.82, "elapsed_time": "3:35:40", "remaining_time": "2:30:58"}
+{"current_steps": 1300, "total_steps": 2193, "loss": 0.422, "learning_rate": 4.2583502485697945e-06, "epoch": 1.7783857729138166, "percentage": 59.28, "elapsed_time": "3:37:06", "remaining_time": "2:29:08"}
+{"current_steps": 1310, "total_steps": 2193, "loss": 0.4278, "learning_rate": 4.179713681256523e-06, "epoch": 1.792065663474692, "percentage": 59.74, "elapsed_time": "3:38:35", "remaining_time": "2:27:20"}
+{"current_steps": 1320, "total_steps": 2193, "loss": 0.4126, "learning_rate": 4.101285084506075e-06, "epoch": 1.8057455540355676, "percentage": 60.19, "elapsed_time": "3:39:55", "remaining_time": "2:25:27"}
+{"current_steps": 1330, "total_steps": 2193, "loss": 0.4302, "learning_rate": 4.023084342643026e-06, "epoch": 1.819425444596443, "percentage": 60.65, "elapsed_time": "3:41:17", "remaining_time": "2:23:35"}
+{"current_steps": 1340, "total_steps": 2193, "loss": 0.4308, "learning_rate": 3.94513128222297e-06, "epoch": 1.8331053351573188, "percentage": 61.1, "elapsed_time": "3:42:47", "remaining_time": "2:21:49"}
+{"current_steps": 1350, "total_steps": 2193, "loss": 0.4343, "learning_rate": 3.867445667005801e-06, "epoch": 1.8467852257181943, "percentage": 61.56, "elapsed_time": "3:44:12", "remaining_time": "2:20:00"}
+{"current_steps": 1360, "total_steps": 2193, "loss": 0.4301, "learning_rate": 3.790047192944931e-06, "epoch": 1.8604651162790697, "percentage": 62.02, "elapsed_time": "3:45:47", "remaining_time": "2:18:17"}
+{"current_steps": 1370, "total_steps": 2193, "loss": 0.4175, "learning_rate": 3.7129554831936998e-06, "epoch": 1.8741450068399452, "percentage": 62.47, "elapsed_time": "3:47:18", "remaining_time": "2:16:33"}
+{"current_steps": 1380, "total_steps": 2193, "loss": 0.4175, "learning_rate": 3.6361900831302264e-06, "epoch": 1.887824897400821, "percentage": 62.93, "elapsed_time": "3:48:54", "remaining_time": "2:14:51"}
+{"current_steps": 1390, "total_steps": 2193, "loss": 0.4211, "learning_rate": 3.5597704554019907e-06, "epoch": 1.9015047879616964, "percentage": 63.38, "elapsed_time": "3:50:20", "remaining_time": "2:13:04"}
+{"current_steps": 1400, "total_steps": 2193, "loss": 0.4195, "learning_rate": 3.4837159749913944e-06, "epoch": 1.915184678522572, "percentage": 63.84, "elapsed_time": "3:51:49", "remaining_time": "2:11:18"}
+{"current_steps": 1400, "total_steps": 2193, "eval_loss": 0.6006618142127991, "epoch": 1.915184678522572, "percentage": 63.84, "elapsed_time": "3:54:36", "remaining_time": "2:12:53"}
+{"current_steps": 1410, "total_steps": 2193, "loss": 0.4205, "learning_rate": 3.40804592430354e-06, "epoch": 1.9288645690834474, "percentage": 64.3, "elapsed_time": "3:56:08", "remaining_time": "2:11:07"}
+{"current_steps": 1420, "total_steps": 2193, "loss": 0.4295, "learning_rate": 3.3327794882774785e-06, "epoch": 1.9425444596443229, "percentage": 64.75, "elapsed_time": "3:57:40", "remaining_time": "2:09:23"}
+{"current_steps": 1430, "total_steps": 2193, "loss": 0.4104, "learning_rate": 3.2579357495221786e-06, "epoch": 1.9562243502051984, "percentage": 65.21, "elapsed_time": "3:59:15", "remaining_time": "2:07:39"}
+{"current_steps": 1440, "total_steps": 2193, "loss": 0.4091, "learning_rate": 3.183533683478427e-06, "epoch": 1.9699042407660738, "percentage": 65.66, "elapsed_time": "4:00:56", "remaining_time": "2:05:59"}
+{"current_steps": 1450, "total_steps": 2193, "loss": 0.43, "learning_rate": 3.1095921536079215e-06, "epoch": 1.9835841313269493, "percentage": 66.12, "elapsed_time": "4:02:24", "remaining_time": "2:04:12"}
+{"current_steps": 1460, "total_steps": 2193, "loss": 0.4146, "learning_rate": 3.0361299066107225e-06, "epoch": 1.9972640218878248, "percentage": 66.58, "elapsed_time": "4:03:51", "remaining_time": "2:02:25"}
+{"current_steps": 1470, "total_steps": 2193, "loss": 0.3057, "learning_rate": 2.9631655676723358e-06, "epoch": 2.0109439124487003, "percentage": 67.03, "elapsed_time": "4:05:26", "remaining_time": "2:00:43"}
+{"current_steps": 1480, "total_steps": 2193, "loss": 0.2671, "learning_rate": 2.890717635741589e-06, "epoch": 2.024623803009576, "percentage": 67.49, "elapsed_time": "4:06:52", "remaining_time": "1:58:56"}
+{"current_steps": 1490, "total_steps": 2193, "loss": 0.2676, "learning_rate": 2.81880447884052e-06, "epoch": 2.0383036935704513, "percentage": 67.94, "elapsed_time": "4:08:26", "remaining_time": "1:57:12"}
+{"current_steps": 1500, "total_steps": 2193, "loss": 0.2593, "learning_rate": 2.7474443294074537e-06, "epoch": 2.0519835841313268, "percentage": 68.4, "elapsed_time": "4:09:58", "remaining_time": "1:55:29"}
+{"current_steps": 1510, "total_steps": 2193, "loss": 0.2703, "learning_rate": 2.6766552796744583e-06, "epoch": 2.0656634746922027, "percentage": 68.86, "elapsed_time": "4:11:21", "remaining_time": "1:53:41"}
+{"current_steps": 1520, "total_steps": 2193, "loss": 0.2708, "learning_rate": 2.606455277080346e-06, "epoch": 2.079343365253078, "percentage": 69.31, "elapsed_time": "4:12:54", "remaining_time": "1:51:58"}
+{"current_steps": 1530, "total_steps": 2193, "loss": 0.2664, "learning_rate": 2.536862119720387e-06, "epoch": 2.0930232558139537, "percentage": 69.77, "elapsed_time": "4:14:27", "remaining_time": "1:50:15"}
+{"current_steps": 1540, "total_steps": 2193, "loss": 0.2673, "learning_rate": 2.467893451833884e-06, "epoch": 2.106703146374829, "percentage": 70.22, "elapsed_time": "4:16:09", "remaining_time": "1:48:37"}
+{"current_steps": 1550, "total_steps": 2193, "loss": 0.2622, "learning_rate": 2.3995667593307563e-06, "epoch": 2.1203830369357046, "percentage": 70.68, "elapsed_time": "4:17:37", "remaining_time": "1:46:52"}
+{"current_steps": 1560, "total_steps": 2193, "loss": 0.2695, "learning_rate": 2.331899365358266e-06, "epoch": 2.13406292749658, "percentage": 71.14, "elapsed_time": "4:19:10", "remaining_time": "1:45:09"}
+{"current_steps": 1570, "total_steps": 2193, "loss": 0.2593, "learning_rate": 2.2649084259090058e-06, "epoch": 2.1477428180574556, "percentage": 71.59, "elapsed_time": "4:20:40", "remaining_time": "1:43:26"}
+{"current_steps": 1580, "total_steps": 2193, "loss": 0.2708, "learning_rate": 2.1986109254712745e-06, "epoch": 2.161422708618331, "percentage": 72.05, "elapsed_time": "4:22:10", "remaining_time": "1:41:43"}
+{"current_steps": 1590, "total_steps": 2193, "loss": 0.2697, "learning_rate": 2.133023672722923e-06, "epoch": 2.1751025991792066, "percentage": 72.5, "elapsed_time": "4:23:37", "remaining_time": "1:39:58"}
+{"current_steps": 1600, "total_steps": 2193, "loss": 0.2528, "learning_rate": 2.0681632962697955e-06, "epoch": 2.188782489740082, "percentage": 72.96, "elapsed_time": "4:25:10", "remaining_time": "1:38:16"}
+{"current_steps": 1600, "total_steps": 2193, "eval_loss": 0.6378765106201172, "epoch": 2.188782489740082, "percentage": 72.96, "elapsed_time": "4:28:01", "remaining_time": "1:39:20"}
+{"current_steps": 1610, "total_steps": 2193, "loss": 0.2719, "learning_rate": 2.0040462404297873e-06, "epoch": 2.2024623803009575, "percentage": 73.42, "elapsed_time": "4:29:28", "remaining_time": "1:37:34"}
+{"current_steps": 1620, "total_steps": 2193, "loss": 0.2659, "learning_rate": 1.9406887610636716e-06, "epoch": 2.216142270861833, "percentage": 73.87, "elapsed_time": "4:30:55", "remaining_time": "1:35:49"}
+{"current_steps": 1630, "total_steps": 2193, "loss": 0.2677, "learning_rate": 1.8781069214536711e-06, "epoch": 2.2298221614227085, "percentage": 74.33, "elapsed_time": "4:32:27", "remaining_time": "1:34:06"}
+{"current_steps": 1640, "total_steps": 2193, "loss": 0.2662, "learning_rate": 1.8163165882308776e-06, "epoch": 2.243502051983584, "percentage": 74.78, "elapsed_time": "4:33:56", "remaining_time": "1:32:22"}
+{"current_steps": 1650, "total_steps": 2193, "loss": 0.2648, "learning_rate": 1.7553334273525107e-06, "epoch": 2.2571819425444595, "percentage": 75.24, "elapsed_time": "4:35:33", "remaining_time": "1:30:41"}
+{"current_steps": 1660, "total_steps": 2193, "loss": 0.2659, "learning_rate": 1.6951729001300626e-06, "epoch": 2.270861833105335, "percentage": 75.7, "elapsed_time": "4:36:58", "remaining_time": "1:28:55"}
+{"current_steps": 1670, "total_steps": 2193, "loss": 0.2638, "learning_rate": 1.6358502593093417e-06, "epoch": 2.2845417236662104, "percentage": 76.15, "elapsed_time": "4:38:26", "remaining_time": "1:27:12"}
+{"current_steps": 1680, "total_steps": 2193, "loss": 0.2647, "learning_rate": 1.5773805452033664e-06, "epoch": 2.2982216142270864, "percentage": 76.61, "elapsed_time": "4:39:45", "remaining_time": "1:25:25"}
+{"current_steps": 1690, "total_steps": 2193, "loss": 0.2611, "learning_rate": 1.5197785818791395e-06, "epoch": 2.311901504787962, "percentage": 77.06, "elapsed_time": "4:41:20", "remaining_time": "1:23:44"}
+{"current_steps": 1700, "total_steps": 2193, "loss": 0.2597, "learning_rate": 1.463058973399241e-06, "epoch": 2.3255813953488373, "percentage": 77.52, "elapsed_time": "4:42:54", "remaining_time": "1:22:02"}
+{"current_steps": 1710, "total_steps": 2193, "loss": 0.2664, "learning_rate": 1.4072361001191997e-06, "epoch": 2.339261285909713, "percentage": 77.98, "elapsed_time": "4:44:25", "remaining_time": "1:20:20"}
+{"current_steps": 1720, "total_steps": 2193, "loss": 0.2579, "learning_rate": 1.3523241150415822e-06, "epoch": 2.3529411764705883, "percentage": 78.43, "elapsed_time": "4:46:02", "remaining_time": "1:18:39"}
+{"current_steps": 1730, "total_steps": 2193, "loss": 0.2627, "learning_rate": 1.298336940227724e-06, "epoch": 2.366621067031464, "percentage": 78.89, "elapsed_time": "4:47:32", "remaining_time": "1:16:57"}
+{"current_steps": 1740, "total_steps": 2193, "loss": 0.2629, "learning_rate": 1.2452882632680125e-06, "epoch": 2.3803009575923393, "percentage": 79.34, "elapsed_time": "4:49:04", "remaining_time": "1:15:15"}
+{"current_steps": 1750, "total_steps": 2193, "loss": 0.2579, "learning_rate": 1.1931915338116157e-06, "epoch": 2.3939808481532148, "percentage": 79.8, "elapsed_time": "4:50:42", "remaining_time": "1:13:35"}
+{"current_steps": 1760, "total_steps": 2193, "loss": 0.2655, "learning_rate": 1.1420599601565375e-06, "epoch": 2.4076607387140903, "percentage": 80.26, "elapsed_time": "4:52:10", "remaining_time": "1:11:52"}
+{"current_steps": 1770, "total_steps": 2193, "loss": 0.2614, "learning_rate": 1.0919065059008626e-06, "epoch": 2.4213406292749657, "percentage": 80.71, "elapsed_time": "4:53:46", "remaining_time": "1:10:12"}
+{"current_steps": 1780, "total_steps": 2193, "loss": 0.2633, "learning_rate": 1.042743886656043e-06, "epoch": 2.4350205198358412, "percentage": 81.17, "elapsed_time": "4:55:21", "remaining_time": "1:08:31"}
+{"current_steps": 1790, "total_steps": 2193, "loss": 0.2626, "learning_rate": 9.94584566823062e-07, "epoch": 2.4487004103967167, "percentage": 81.62, "elapsed_time": "4:56:51", "remaining_time": "1:06:50"}
+{"current_steps": 1800, "total_steps": 2193, "loss": 0.2648, "learning_rate": 9.474407564322685e-07, "epoch": 2.462380300957592, "percentage": 82.08, "elapsed_time": "4:58:23", "remaining_time": "1:05:08"}
+{"current_steps": 1800, "total_steps": 2193, "eval_loss": 0.6390905976295471, "epoch": 2.462380300957592, "percentage": 82.08, "elapsed_time": "5:01:10", "remaining_time": "1:05:45"}
+{"current_steps": 1810, "total_steps": 2193, "loss": 0.2649, "learning_rate": 9.01324408047734e-07, "epoch": 2.4760601915184677, "percentage": 82.54, "elapsed_time": "5:02:42", "remaining_time": "1:04:03"}
+{"current_steps": 1820, "total_steps": 2193, "loss": 0.2598, "learning_rate": 8.562472137368638e-07, "epoch": 2.4897400820793436, "percentage": 82.99, "elapsed_time": "5:04:10", "remaining_time": "1:02:20"}
+{"current_steps": 1830, "total_steps": 2193, "loss": 0.2627, "learning_rate": 8.122206021060552e-07, "epoch": 2.503419972640219, "percentage": 83.45, "elapsed_time": "5:05:41", "remaining_time": "1:00:38"}
+{"current_steps": 1840, "total_steps": 2193, "loss": 0.2554, "learning_rate": 7.692557354031633e-07, "epoch": 2.5170998632010946, "percentage": 83.9, "elapsed_time": "5:07:10", "remaining_time": "0:58:55"}
+{"current_steps": 1850, "total_steps": 2193, "loss": 0.2595, "learning_rate": 7.273635066874796e-07, "epoch": 2.53077975376197, "percentage": 84.36, "elapsed_time": "5:08:46", "remaining_time": "0:57:14"}
+{"current_steps": 1860, "total_steps": 2193, "loss": 0.2562, "learning_rate": 6.86554537067986e-07, "epoch": 2.5444596443228455, "percentage": 84.82, "elapsed_time": "5:10:10", "remaining_time": "0:55:31"}
+{"current_steps": 1870, "total_steps": 2193, "loss": 0.2589, "learning_rate": 6.46839173010525e-07, "epoch": 2.558139534883721, "percentage": 85.27, "elapsed_time": "5:11:32", "remaining_time": "0:53:48"}
+{"current_steps": 1880, "total_steps": 2193, "loss": 0.2565, "learning_rate": 6.08227483714629e-07, "epoch": 2.5718194254445965, "percentage": 85.73, "elapsed_time": "5:12:56", "remaining_time": "0:52:06"}
+{"current_steps": 1890, "total_steps": 2193, "loss": 0.2646, "learning_rate": 5.707292585606277e-07, "epoch": 2.585499316005472, "percentage": 86.18, "elapsed_time": "5:14:25", "remaining_time": "0:50:24"}
+{"current_steps": 1900, "total_steps": 2193, "loss": 0.2571, "learning_rate": 5.343540046277113e-07, "epoch": 2.5991792065663475, "percentage": 86.64, "elapsed_time": "5:15:50", "remaining_time": "0:48:42"}
+{"current_steps": 1910, "total_steps": 2193, "loss": 0.2605, "learning_rate": 4.991109442835578e-07, "epoch": 2.612859097127223, "percentage": 87.1, "elapsed_time": "5:17:14", "remaining_time": "0:47:00"}
+{"current_steps": 1920, "total_steps": 2193, "loss": 0.2621, "learning_rate": 4.6500901284615094e-07, "epoch": 2.6265389876880985, "percentage": 87.55, "elapsed_time": "5:18:44", "remaining_time": "0:45:19"}
+{"current_steps": 1930, "total_steps": 2193, "loss": 0.2646, "learning_rate": 4.320568563183708e-07, "epoch": 2.640218878248974, "percentage": 88.01, "elapsed_time": "5:20:17", "remaining_time": "0:43:38"}
+{"current_steps": 1940, "total_steps": 2193, "loss": 0.2653, "learning_rate": 4.0026282919593815e-07, "epoch": 2.6538987688098494, "percentage": 88.46, "elapsed_time": "5:21:57", "remaining_time": "0:41:59"}
+{"current_steps": 1950, "total_steps": 2193, "loss": 0.2675, "learning_rate": 3.6963499234926314e-07, "epoch": 2.667578659370725, "percentage": 88.92, "elapsed_time": "5:23:33", "remaining_time": "0:40:19"}
+{"current_steps": 1960, "total_steps": 2193, "loss": 0.2805, "learning_rate": 3.401811109797404e-07, "epoch": 2.6812585499316004, "percentage": 89.38, "elapsed_time": "5:25:05", "remaining_time": "0:38:38"}
+{"current_steps": 1970, "total_steps": 2193, "loss": 0.2594, "learning_rate": 3.1190865265100954e-07, "epoch": 2.694938440492476, "percentage": 89.83, "elapsed_time": "5:26:46", "remaining_time": "0:36:59"}
+{"current_steps": 1980, "total_steps": 2193, "loss": 0.2662, "learning_rate": 2.8482478539566595e-07, "epoch": 2.7086183310533514, "percentage": 90.29, "elapsed_time": "5:28:21", "remaining_time": "0:35:19"}
+{"current_steps": 1990, "total_steps": 2193, "loss": 0.2688, "learning_rate": 2.58936375897923e-07, "epoch": 2.722298221614227, "percentage": 90.74, "elapsed_time": "5:29:51", "remaining_time": "0:33:38"}
+{"current_steps": 2000, "total_steps": 2193, "loss": 0.2586, "learning_rate": 2.342499877526755e-07, "epoch": 2.7359781121751023, "percentage": 91.2, "elapsed_time": "5:31:26", "remaining_time": "0:31:59"}
+{"current_steps": 2000, "total_steps": 2193, "eval_loss": 0.6391583681106567, "epoch": 2.7359781121751023, "percentage": 91.2, "elapsed_time": "5:34:14", "remaining_time": "0:32:15"}
+{"current_steps": 2010, "total_steps": 2193, "loss": 0.2616, "learning_rate": 2.1077187980140467e-07, "epoch": 2.7496580027359783, "percentage": 91.66, "elapsed_time": "5:37:07", "remaining_time": "0:30:41"}
+{"current_steps": 2020, "total_steps": 2193, "loss": 0.2591, "learning_rate": 1.8850800454534358e-07, "epoch": 2.7633378932968538, "percentage": 92.11, "elapsed_time": "5:38:40", "remaining_time": "0:29:00"}
+{"current_steps": 2030, "total_steps": 2193, "loss": 0.2608, "learning_rate": 1.6746400663631923e-07, "epoch": 2.7770177838577292, "percentage": 92.57, "elapsed_time": "5:40:23", "remaining_time": "0:27:19"}
+{"current_steps": 2040, "total_steps": 2193, "loss": 0.2625, "learning_rate": 1.4764522144563865e-07, "epoch": 2.7906976744186047, "percentage": 93.02, "elapsed_time": "5:41:46", "remaining_time": "0:25:37"}
+{"current_steps": 2050, "total_steps": 2193, "loss": 0.259, "learning_rate": 1.2905667371139298e-07, "epoch": 2.80437756497948, "percentage": 93.48, "elapsed_time": "5:43:16", "remaining_time": "0:23:56"}
+{"current_steps": 2060, "total_steps": 2193, "loss": 0.2613, "learning_rate": 1.117030762645116e-07, "epoch": 2.8180574555403557, "percentage": 93.94, "elapsed_time": "5:44:56", "remaining_time": "0:22:16"}
+{"current_steps": 2070, "total_steps": 2193, "loss": 0.2607, "learning_rate": 9.558882883390075e-08, "epoch": 2.831737346101231, "percentage": 94.39, "elapsed_time": "5:46:33", "remaining_time": "0:20:35"}
+{"current_steps": 2080, "total_steps": 2193, "loss": 0.2575, "learning_rate": 8.071801693096237e-08, "epoch": 2.8454172366621067, "percentage": 94.85, "elapsed_time": "5:48:02", "remaining_time": "0:18:54"}
+{"current_steps": 2090, "total_steps": 2193, "loss": 0.2601, "learning_rate": 6.70944108137761e-08, "epoch": 2.859097127222982, "percentage": 95.3, "elapsed_time": "5:49:26", "remaining_time": "0:17:13"}
+{"current_steps": 2100, "total_steps": 2193, "loss": 0.2565, "learning_rate": 5.472146453121163e-08, "epoch": 2.8727770177838576, "percentage": 95.76, "elapsed_time": "5:51:02", "remaining_time": "0:15:32"}
+{"current_steps": 2110, "total_steps": 2193, "loss": 0.2726, "learning_rate": 4.360231504720813e-08, "epoch": 2.886456908344733, "percentage": 96.22, "elapsed_time": "5:52:36", "remaining_time": "0:13:52"}
+{"current_steps": 2120, "total_steps": 2193, "loss": 0.2544, "learning_rate": 3.3739781445449316e-08, "epoch": 2.9001367989056086, "percentage": 96.67, "elapsed_time": "5:54:08", "remaining_time": "0:12:11"}
+{"current_steps": 2130, "total_steps": 2193, "loss": 0.2587, "learning_rate": 2.513636421462573e-08, "epoch": 2.9138166894664845, "percentage": 97.13, "elapsed_time": "5:55:33", "remaining_time": "0:10:30"}
+{"current_steps": 2140, "total_steps": 2193, "loss": 0.2622, "learning_rate": 1.779424461447965e-08, "epoch": 2.92749658002736, "percentage": 97.58, "elapsed_time": "5:57:05", "remaining_time": "0:08:50"}
+{"current_steps": 2150, "total_steps": 2193, "loss": 0.261, "learning_rate": 1.1715284122779114e-08, "epoch": 2.9411764705882355, "percentage": 98.04, "elapsed_time": "5:58:34", "remaining_time": "0:07:10"}
+{"current_steps": 2160, "total_steps": 2193, "loss": 0.2581, "learning_rate": 6.901023963369336e-09, "epoch": 2.954856361149111, "percentage": 98.5, "elapsed_time": "6:00:12", "remaining_time": "0:05:30"}
+{"current_steps": 2170, "total_steps": 2193, "loss": 0.2577, "learning_rate": 3.3526847154219387e-09, "epoch": 2.9685362517099865, "percentage": 98.95, "elapsed_time": "6:01:44", "remaining_time": "0:03:50"}
+{"current_steps": 2180, "total_steps": 2193, "loss": 0.2691, "learning_rate": 1.0711660039747219e-09, "epoch": 2.982216142270862, "percentage": 99.41, "elapsed_time": "6:03:14", "remaining_time": "0:02:09"}
+{"current_steps": 2190, "total_steps": 2193, "loss": 0.2604, "learning_rate": 5.704627184577316e-11, "epoch": 2.9958960328317374, "percentage": 99.86, "elapsed_time": "6:04:44", "remaining_time": "0:00:29"}
+{"current_steps": 2193, "total_steps": 2193, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "6:06:33", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1655 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 200,
+  "global_step": 2193,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013679890560875513,
+      "grad_norm": 4.306338197381437,
+      "learning_rate": 4.5454545454545457e-07,
+      "loss": 0.9255,
+      "step": 10
+    },
+    {
+      "epoch": 0.027359781121751026,
+      "grad_norm": 2.40394571117872,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 0.863,
+      "step": 20
+    },
+    {
+      "epoch": 0.04103967168262654,
+      "grad_norm": 1.8078902930615164,
+      "learning_rate": 1.3636363636363636e-06,
+      "loss": 0.7599,
+      "step": 30
+    },
+    {
+      "epoch": 0.05471956224350205,
+      "grad_norm": 1.4220385901238113,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 0.7184,
+      "step": 40
+    },
+    {
+      "epoch": 0.06839945280437756,
+      "grad_norm": 1.3537605726648354,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 0.6981,
+      "step": 50
+    },
+    {
+      "epoch": 0.08207934336525308,
+      "grad_norm": 1.2344983469823567,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 0.6943,
+      "step": 60
+    },
+    {
+      "epoch": 0.09575923392612859,
+      "grad_norm": 1.1119101183337694,
+      "learning_rate": 3.181818181818182e-06,
+      "loss": 0.6687,
+      "step": 70
+    },
+    {
+      "epoch": 0.1094391244870041,
+      "grad_norm": 1.2164492298241776,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 0.6694,
+      "step": 80
+    },
+    {
+      "epoch": 0.12311901504787962,
+      "grad_norm": 1.3446219804481927,
+      "learning_rate": 4.0909090909090915e-06,
+      "loss": 0.6602,
+      "step": 90
+    },
+    {
+      "epoch": 0.13679890560875513,
+      "grad_norm": 1.2505229649313154,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.6514,
+      "step": 100
+    },
+    {
+      "epoch": 0.15047879616963064,
+      "grad_norm": 1.1279331262953187,
+      "learning_rate": 5e-06,
+      "loss": 0.6413,
+      "step": 110
+    },
+    {
+      "epoch": 0.16415868673050615,
+      "grad_norm": 1.246045877795659,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 0.6584,
+      "step": 120
+    },
+    {
+      "epoch": 0.17783857729138167,
+      "grad_norm": 1.1785589469428788,
+      "learning_rate": 5.90909090909091e-06,
+      "loss": 0.6292,
+      "step": 130
+    },
+    {
+      "epoch": 0.19151846785225718,
+      "grad_norm": 1.219408849788821,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 0.6487,
+      "step": 140
+    },
+    {
+      "epoch": 0.2051983584131327,
+      "grad_norm": 1.1571538455846238,
+      "learning_rate": 6.818181818181818e-06,
+      "loss": 0.6294,
+      "step": 150
+    },
+    {
+      "epoch": 0.2188782489740082,
+      "grad_norm": 1.3558018996617476,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 0.6443,
+      "step": 160
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 1.5617060190415994,
+      "learning_rate": 7.727272727272727e-06,
+      "loss": 0.6411,
+      "step": 170
+    },
+    {
+      "epoch": 0.24623803009575923,
+      "grad_norm": 1.235429384148413,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 0.6385,
+      "step": 180
+    },
+    {
+      "epoch": 0.25991792065663477,
+      "grad_norm": 1.2646278028286053,
+      "learning_rate": 8.636363636363637e-06,
+      "loss": 0.6466,
+      "step": 190
+    },
+    {
+      "epoch": 0.27359781121751026,
+      "grad_norm": 1.3092856333044969,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.6185,
+      "step": 200
+    },
+    {
+      "epoch": 0.27359781121751026,
+      "eval_loss": 0.6430878043174744,
+      "eval_runtime": 168.6747,
+      "eval_samples_per_second": 30.817,
+      "eval_steps_per_second": 3.854,
+      "step": 200
+    },
+    {
+      "epoch": 0.2872777017783858,
+      "grad_norm": 1.1897854638522036,
+      "learning_rate": 9.545454545454547e-06,
+      "loss": 0.6235,
+      "step": 210
+    },
+    {
+      "epoch": 0.3009575923392613,
+      "grad_norm": 1.249148897978773,
+      "learning_rate": 1e-05,
+      "loss": 0.6305,
+      "step": 220
+    },
+    {
+      "epoch": 0.3146374829001368,
+      "grad_norm": 1.1885808643667615,
+      "learning_rate": 9.99936616472178e-06,
+      "loss": 0.6308,
+      "step": 230
+    },
+    {
+      "epoch": 0.3283173734610123,
+      "grad_norm": 1.250733802249208,
+      "learning_rate": 9.997464819585985e-06,
+      "loss": 0.6331,
+      "step": 240
+    },
+    {
+      "epoch": 0.34199726402188785,
+      "grad_norm": 1.1199745780436605,
+      "learning_rate": 9.994296446648463e-06,
+      "loss": 0.6319,
+      "step": 250
+    },
+    {
+      "epoch": 0.35567715458276333,
+      "grad_norm": 1.1180646470383142,
+      "learning_rate": 9.989861849199833e-06,
+      "loss": 0.6368,
+      "step": 260
+    },
+    {
+      "epoch": 0.3693570451436389,
+      "grad_norm": 1.1411785528368101,
+      "learning_rate": 9.984162151561814e-06,
+      "loss": 0.628,
+      "step": 270
+    },
+    {
+      "epoch": 0.38303693570451436,
+      "grad_norm": 1.0640206569253472,
+      "learning_rate": 9.977198798802186e-06,
+      "loss": 0.6191,
+      "step": 280
+    },
+    {
+      "epoch": 0.3967168262653899,
+      "grad_norm": 1.2307131395813051,
+      "learning_rate": 9.9689735563684e-06,
+      "loss": 0.6311,
+      "step": 290
+    },
+    {
+      "epoch": 0.4103967168262654,
+      "grad_norm": 1.1751145352265429,
+      "learning_rate": 9.959488509639986e-06,
+      "loss": 0.6204,
+      "step": 300
+    },
+    {
+      "epoch": 0.4240766073871409,
+      "grad_norm": 1.1381135969095364,
+      "learning_rate": 9.948746063399836e-06,
+      "loss": 0.6185,
+      "step": 310
+    },
+    {
+      "epoch": 0.4377564979480164,
+      "grad_norm": 1.2008146993612843,
+      "learning_rate": 9.936748941224514e-06,
+      "loss": 0.63,
+      "step": 320
+    },
+    {
+      "epoch": 0.45143638850889195,
+      "grad_norm": 1.0906550245462099,
+      "learning_rate": 9.923500184793728e-06,
+      "loss": 0.6325,
+      "step": 330
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 1.2687828199372913,
+      "learning_rate": 9.909003153119165e-06,
+      "loss": 0.6202,
+      "step": 340
+    },
+    {
+      "epoch": 0.478796169630643,
+      "grad_norm": 1.2051295685227352,
+      "learning_rate": 9.893261521692865e-06,
+      "loss": 0.6157,
+      "step": 350
+    },
+    {
+      "epoch": 0.49247606019151846,
+      "grad_norm": 1.1391781521048607,
+      "learning_rate": 9.876279281555363e-06,
+      "loss": 0.6244,
+      "step": 360
+    },
+    {
+      "epoch": 0.506155950752394,
+      "grad_norm": 1.0911712689339368,
+      "learning_rate": 9.858060738283819e-06,
+      "loss": 0.6209,
+      "step": 370
+    },
+    {
+      "epoch": 0.5198358413132695,
+      "grad_norm": 1.1210123313032032,
+      "learning_rate": 9.838610510900412e-06,
+      "loss": 0.6168,
+      "step": 380
+    },
+    {
+      "epoch": 0.533515731874145,
+      "grad_norm": 1.2189445592306896,
+      "learning_rate": 9.817933530701258e-06,
+      "loss": 0.6273,
+      "step": 390
+    },
+    {
+      "epoch": 0.5471956224350205,
+      "grad_norm": 1.0483395986247415,
+      "learning_rate": 9.79603504000615e-06,
+      "loss": 0.6088,
+      "step": 400
+    },
+    {
+      "epoch": 0.5471956224350205,
+      "eval_loss": 0.6271325945854187,
+      "eval_runtime": 167.7353,
+      "eval_samples_per_second": 30.989,
+      "eval_steps_per_second": 3.875,
+      "step": 400
+    },
+    {
+      "epoch": 0.560875512995896,
+      "grad_norm": 1.0660522163415433,
+      "learning_rate": 9.772920590829471e-06,
+      "loss": 0.6137,
+      "step": 410
+    },
+    {
+      "epoch": 0.5745554035567716,
+      "grad_norm": 1.2363091668613064,
+      "learning_rate": 9.748596043472547e-06,
+      "loss": 0.6143,
+      "step": 420
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 1.0981082723618094,
+      "learning_rate": 9.723067565037874e-06,
+      "loss": 0.6068,
+      "step": 430
+    },
+    {
+      "epoch": 0.6019151846785226,
+      "grad_norm": 1.1847772259009521,
+      "learning_rate": 9.696341627865548e-06,
+      "loss": 0.6263,
+      "step": 440
+    },
+    {
+      "epoch": 0.615595075239398,
+      "grad_norm": 1.179605990278435,
+      "learning_rate": 9.668425007892298e-06,
+      "loss": 0.624,
+      "step": 450
+    },
+    {
+      "epoch": 0.6292749658002736,
+      "grad_norm": 1.1327982969979666,
+      "learning_rate": 9.639324782933556e-06,
+      "loss": 0.6115,
+      "step": 460
+    },
+    {
+      "epoch": 0.6429548563611491,
+      "grad_norm": 1.1092926273561299,
+      "learning_rate": 9.609048330888996e-06,
+      "loss": 0.6231,
+      "step": 470
+    },
+    {
+      "epoch": 0.6566347469220246,
+      "grad_norm": 1.2023856216186377,
+      "learning_rate": 9.577603327871983e-06,
+      "loss": 0.6087,
+      "step": 480
+    },
+    {
+      "epoch": 0.6703146374829001,
+      "grad_norm": 1.140079893396528,
+      "learning_rate": 9.544997746263409e-06,
+      "loss": 0.6207,
+      "step": 490
+    },
+    {
+      "epoch": 0.6839945280437757,
+      "grad_norm": 1.0956555350394377,
+      "learning_rate": 9.511239852690429e-06,
+      "loss": 0.5912,
+      "step": 500
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 1.0991687302711715,
+      "learning_rate": 9.476338205930593e-06,
+      "loss": 0.6084,
+      "step": 510
+    },
+    {
+      "epoch": 0.7113543091655267,
+      "grad_norm": 1.0969007693966542,
+      "learning_rate": 9.440301654741889e-06,
+      "loss": 0.6132,
+      "step": 520
+    },
+    {
+      "epoch": 0.7250341997264022,
+      "grad_norm": 1.1125573118122185,
+      "learning_rate": 9.403139335619302e-06,
+      "loss": 0.6194,
+      "step": 530
+    },
+    {
+      "epoch": 0.7387140902872777,
+      "grad_norm": 1.1809078700930535,
+      "learning_rate": 9.36486067047838e-06,
+      "loss": 0.5951,
+      "step": 540
+    },
+    {
+      "epoch": 0.7523939808481532,
+      "grad_norm": 1.1864929076204318,
+      "learning_rate": 9.325475364266474e-06,
+      "loss": 0.6007,
+      "step": 550
+    },
+    {
+      "epoch": 0.7660738714090287,
+      "grad_norm": 1.26583782519778,
+      "learning_rate": 9.28499340250219e-06,
+      "loss": 0.6146,
+      "step": 560
+    },
+    {
+      "epoch": 0.7797537619699042,
+      "grad_norm": 1.076257354571428,
+      "learning_rate": 9.24342504874373e-06,
+      "loss": 0.6077,
+      "step": 570
+    },
+    {
+      "epoch": 0.7934336525307798,
+      "grad_norm": 1.0622000039574993,
+      "learning_rate": 9.200780841986717e-06,
+      "loss": 0.6001,
+      "step": 580
+    },
+    {
+      "epoch": 0.8071135430916553,
+      "grad_norm": 1.188474169737116,
+      "learning_rate": 9.157071593992217e-06,
+      "loss": 0.6289,
+      "step": 590
+    },
+    {
+      "epoch": 0.8207934336525308,
+      "grad_norm": 1.1602582650897655,
+      "learning_rate": 9.112308386545574e-06,
+      "loss": 0.6083,
+      "step": 600
+    },
+    {
+      "epoch": 0.8207934336525308,
+      "eval_loss": 0.6138648390769958,
+      "eval_runtime": 169.037,
+      "eval_samples_per_second": 30.751,
+      "eval_steps_per_second": 3.845,
+      "step": 600
+    },
+    {
+      "epoch": 0.8344733242134063,
+      "grad_norm": 1.1422692672202526,
+      "learning_rate": 9.066502568646805e-06,
+      "loss": 0.6028,
+      "step": 610
+    },
+    {
+      "epoch": 0.8481532147742818,
+      "grad_norm": 1.1671002032829694,
+      "learning_rate": 9.019665753633247e-06,
+      "loss": 0.6025,
+      "step": 620
+    },
+    {
+      "epoch": 0.8618331053351573,
+      "grad_norm": 1.1006027336870072,
+      "learning_rate": 8.971809816235164e-06,
+      "loss": 0.6072,
+      "step": 630
+    },
+    {
+      "epoch": 0.8755129958960328,
+      "grad_norm": 1.14419096908491,
+      "learning_rate": 8.922946889565119e-06,
+      "loss": 0.6014,
+      "step": 640
+    },
+    {
+      "epoch": 0.8891928864569083,
+      "grad_norm": 1.1499692013955807,
+      "learning_rate": 8.873089362041797e-06,
+      "loss": 0.584,
+      "step": 650
+    },
+    {
+      "epoch": 0.9028727770177839,
+      "grad_norm": 1.0137383119426882,
+      "learning_rate": 8.822249874249131e-06,
+      "loss": 0.5929,
+      "step": 660
+    },
+    {
+      "epoch": 0.9165526675786594,
+      "grad_norm": 1.0739771517494396,
+      "learning_rate": 8.770441315731477e-06,
+      "loss": 0.5954,
+      "step": 670
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 1.066521535106681,
+      "learning_rate": 8.717676821725679e-06,
+      "loss": 0.5876,
+      "step": 680
+    },
+    {
+      "epoch": 0.9439124487004104,
+      "grad_norm": 1.1050537240337106,
+      "learning_rate": 8.663969769830824e-06,
+      "loss": 0.6006,
+      "step": 690
+    },
+    {
+      "epoch": 0.957592339261286,
+      "grad_norm": 1.0834708122941283,
+      "learning_rate": 8.609333776616592e-06,
+      "loss": 0.5974,
+      "step": 700
+    },
+    {
+      "epoch": 0.9712722298221614,
+      "grad_norm": 1.2256953791044325,
+      "learning_rate": 8.553782694170963e-06,
+      "loss": 0.6043,
+      "step": 710
+    },
+    {
+      "epoch": 0.9849521203830369,
+      "grad_norm": 1.0369686902126203,
+      "learning_rate": 8.497330606588257e-06,
+      "loss": 0.5779,
+      "step": 720
+    },
+    {
+      "epoch": 0.9986320109439124,
+      "grad_norm": 1.0669076543876443,
+      "learning_rate": 8.439991826398331e-06,
+      "loss": 0.6108,
+      "step": 730
+    },
+    {
+      "epoch": 1.012311901504788,
+      "grad_norm": 1.38284058642527,
+      "learning_rate": 8.38178089093786e-06,
+      "loss": 0.4662,
+      "step": 740
+    },
+    {
+      "epoch": 1.0259917920656634,
+      "grad_norm": 1.36236398170643,
+      "learning_rate": 8.322712558664635e-06,
+      "loss": 0.4296,
+      "step": 750
+    },
+    {
+      "epoch": 1.039671682626539,
+      "grad_norm": 1.2100527044799618,
+      "learning_rate": 8.262801805415783e-06,
+      "loss": 0.4295,
+      "step": 760
+    },
+    {
+      "epoch": 1.0533515731874146,
+      "grad_norm": 1.1588309328691597,
+      "learning_rate": 8.202063820610887e-06,
+      "loss": 0.4244,
+      "step": 770
+    },
+    {
+      "epoch": 1.06703146374829,
+      "grad_norm": 1.1590821782151508,
+      "learning_rate": 8.140514003400945e-06,
+      "loss": 0.4257,
+      "step": 780
+    },
+    {
+      "epoch": 1.0807113543091655,
+      "grad_norm": 1.1515662295268354,
+      "learning_rate": 8.078167958764162e-06,
+      "loss": 0.4325,
+      "step": 790
+    },
+    {
+      "epoch": 1.094391244870041,
+      "grad_norm": 1.1972938041742296,
+      "learning_rate": 8.015041493549562e-06,
+      "loss": 0.4314,
+      "step": 800
+    },
+    {
+      "epoch": 1.094391244870041,
+      "eval_loss": 0.6188511848449707,
+      "eval_runtime": 168.4076,
+      "eval_samples_per_second": 30.866,
+      "eval_steps_per_second": 3.86,
+      "step": 800
+    },
+    {
+      "epoch": 1.1080711354309165,
+      "grad_norm": 1.2310788704520765,
+      "learning_rate": 7.951150612469396e-06,
+      "loss": 0.4335,
+      "step": 810
+    },
+    {
+      "epoch": 1.121751025991792,
+      "grad_norm": 1.2391064990548075,
+      "learning_rate": 7.886511514041422e-06,
+      "loss": 0.4271,
+      "step": 820
+    },
+    {
+      "epoch": 1.1354309165526675,
+      "grad_norm": 1.1957485922230724,
+      "learning_rate": 7.821140586482013e-06,
+      "loss": 0.4367,
+      "step": 830
+    },
+    {
+      "epoch": 1.1491108071135432,
+      "grad_norm": 1.2204287898575044,
+      "learning_rate": 7.755054403551191e-06,
+      "loss": 0.4359,
+      "step": 840
+    },
+    {
+      "epoch": 1.1627906976744187,
+      "grad_norm": 1.2398786083740503,
+      "learning_rate": 7.688269720350616e-06,
+      "loss": 0.433,
+      "step": 850
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 1.1869051225812688,
+      "learning_rate": 7.620803469075588e-06,
+      "loss": 0.4387,
+      "step": 860
+    },
+    {
+      "epoch": 1.1901504787961696,
+      "grad_norm": 1.1936581208347872,
+      "learning_rate": 7.552672754722169e-06,
+      "loss": 0.4198,
+      "step": 870
+    },
+    {
+      "epoch": 1.2038303693570451,
+      "grad_norm": 1.153245583578447,
+      "learning_rate": 7.483894850750473e-06,
+      "loss": 0.4356,
+      "step": 880
+    },
+    {
+      "epoch": 1.2175102599179206,
+      "grad_norm": 1.2121786191778063,
+      "learning_rate": 7.414487194705258e-06,
+      "loss": 0.4334,
+      "step": 890
+    },
+    {
+      "epoch": 1.231190150478796,
+      "grad_norm": 1.1865361362733824,
+      "learning_rate": 7.344467383794917e-06,
+      "loss": 0.4335,
+      "step": 900
+    },
+    {
+      "epoch": 1.2448700410396718,
+      "grad_norm": 1.2578535517364966,
+      "learning_rate": 7.2738531704299845e-06,
+      "loss": 0.4338,
+      "step": 910
+    },
+    {
+      "epoch": 1.2585499316005473,
+      "grad_norm": 1.208342728404754,
+      "learning_rate": 7.2026624577222855e-06,
+      "loss": 0.4506,
+      "step": 920
+    },
+    {
+      "epoch": 1.2722298221614228,
+      "grad_norm": 1.2293841459842745,
+      "learning_rate": 7.1309132949459e-06,
+      "loss": 0.4356,
+      "step": 930
+    },
+    {
+      "epoch": 1.2859097127222983,
+      "grad_norm": 1.1995897552412818,
+      "learning_rate": 7.058623872961051e-06,
+      "loss": 0.4293,
+      "step": 940
+    },
+    {
+      "epoch": 1.2995896032831737,
+      "grad_norm": 1.3990655945335009,
+      "learning_rate": 6.985812519602094e-06,
+      "loss": 0.4268,
+      "step": 950
+    },
+    {
+      "epoch": 1.3132694938440492,
+      "grad_norm": 1.2252593246536305,
+      "learning_rate": 6.912497695030796e-06,
+      "loss": 0.4286,
+      "step": 960
+    },
+    {
+      "epoch": 1.3269493844049247,
+      "grad_norm": 1.1833071160287538,
+      "learning_rate": 6.838697987056046e-06,
+      "loss": 0.4313,
+      "step": 970
+    },
+    {
+      "epoch": 1.3406292749658002,
+      "grad_norm": 1.1637401442465505,
+      "learning_rate": 6.764432106421223e-06,
+      "loss": 0.4279,
+      "step": 980
+    },
+    {
+      "epoch": 1.3543091655266757,
+      "grad_norm": 1.2180322469819673,
+      "learning_rate": 6.68971888206037e-06,
+      "loss": 0.4305,
+      "step": 990
+    },
+    {
+      "epoch": 1.3679890560875512,
+      "grad_norm": 1.2229086904650939,
+      "learning_rate": 6.614577256324426e-06,
+      "loss": 0.4322,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3679890560875512,
+      "eval_loss": 0.617301881313324,
+      "eval_runtime": 168.0881,
+      "eval_samples_per_second": 30.924,
+      "eval_steps_per_second": 3.867,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3816689466484269,
+      "grad_norm": 1.1947852132614785,
+      "learning_rate": 6.539026280178695e-06,
+      "loss": 0.4279,
+      "step": 1010
+    },
+    {
+      "epoch": 1.3953488372093024,
+      "grad_norm": 1.247192723450866,
+      "learning_rate": 6.46308510837277e-06,
+      "loss": 0.4309,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4090287277701778,
+      "grad_norm": 1.185576441473233,
+      "learning_rate": 6.386772994584156e-06,
+      "loss": 0.4349,
+      "step": 1030
+    },
+    {
+      "epoch": 1.4227086183310533,
+      "grad_norm": 1.129361008569495,
+      "learning_rate": 6.310109286536801e-06,
+      "loss": 0.4232,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4363885088919288,
+      "grad_norm": 1.1431132187777882,
+      "learning_rate": 6.233113421095794e-06,
+      "loss": 0.4355,
+      "step": 1050
+    },
+    {
+      "epoch": 1.4500683994528043,
+      "grad_norm": 1.1747059710212222,
+      "learning_rate": 6.155804919339453e-06,
+      "loss": 0.4286,
+      "step": 1060
+    },
+    {
+      "epoch": 1.46374829001368,
+      "grad_norm": 1.151624752794334,
+      "learning_rate": 6.078203381610064e-06,
+      "loss": 0.4314,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4774281805745555,
+      "grad_norm": 1.2141807720724713,
+      "learning_rate": 6.000328482544532e-06,
+      "loss": 0.4292,
+      "step": 1080
+    },
+    {
+      "epoch": 1.491108071135431,
+      "grad_norm": 1.2395901378501935,
+      "learning_rate": 5.92219996608618e-06,
+      "loss": 0.4295,
+      "step": 1090
+    },
+    {
+      "epoch": 1.5047879616963065,
+      "grad_norm": 1.3241796863033826,
+      "learning_rate": 5.843837640479e-06,
+      "loss": 0.4399,
+      "step": 1100
+    },
+    {
+      "epoch": 1.518467852257182,
+      "grad_norm": 1.1677488632090005,
+      "learning_rate": 5.765261373245567e-06,
+      "loss": 0.424,
+      "step": 1110
+    },
+    {
+      "epoch": 1.5321477428180574,
+      "grad_norm": 1.2084792827131878,
+      "learning_rate": 5.686491086149965e-06,
+      "loss": 0.4285,
+      "step": 1120
+    },
+    {
+      "epoch": 1.545827633378933,
+      "grad_norm": 1.2057361531766408,
+      "learning_rate": 5.60754675014693e-06,
+      "loss": 0.4397,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5595075239398084,
+      "grad_norm": 1.0459853203349079,
+      "learning_rate": 5.528448380318532e-06,
+      "loss": 0.4184,
+      "step": 1140
+    },
+    {
+      "epoch": 1.573187414500684,
+      "grad_norm": 1.1565826426536214,
+      "learning_rate": 5.449216030799667e-06,
+      "loss": 0.4199,
+      "step": 1150
+    },
+    {
+      "epoch": 1.5868673050615594,
+      "grad_norm": 1.337080485300612,
+      "learning_rate": 5.369869789693656e-06,
+      "loss": 0.4392,
+      "step": 1160
+    },
+    {
+      "epoch": 1.6005471956224349,
+      "grad_norm": 1.2455984858098026,
+      "learning_rate": 5.290429773979224e-06,
+      "loss": 0.4337,
+      "step": 1170
+    },
+    {
+      "epoch": 1.6142270861833106,
+      "grad_norm": 1.218208739067707,
+      "learning_rate": 5.2109161244101545e-06,
+      "loss": 0.4448,
+      "step": 1180
+    },
+    {
+      "epoch": 1.627906976744186,
+      "grad_norm": 1.1285789923935337,
+      "learning_rate": 5.1313490004089265e-06,
+      "loss": 0.4286,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6415868673050615,
+      "grad_norm": 1.2264365996543631,
+      "learning_rate": 5.05174857495561e-06,
+      "loss": 0.4368,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6415868673050615,
+      "eval_loss": 0.608180046081543,
+      "eval_runtime": 168.5858,
+      "eval_samples_per_second": 30.833,
+      "eval_steps_per_second": 3.856,
+      "step": 1200
+    },
+    {
+      "epoch": 1.655266757865937,
+      "grad_norm": 1.243465209947156,
+      "learning_rate": 4.972135029473333e-06,
+      "loss": 0.4276,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6689466484268127,
+      "grad_norm": 1.1806815681626925,
+      "learning_rate": 4.892528548711594e-06,
+      "loss": 0.4334,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6826265389876882,
+      "grad_norm": 1.1380113337270097,
+      "learning_rate": 4.812949315628746e-06,
+      "loss": 0.4272,
+      "step": 1230
+    },
+    {
+      "epoch": 1.6963064295485637,
+      "grad_norm": 1.1677234792880147,
+      "learning_rate": 4.7334175062749275e-06,
+      "loss": 0.4164,
+      "step": 1240
+    },
+    {
+      "epoch": 1.7099863201094392,
+      "grad_norm": 1.1552072694954474,
+      "learning_rate": 4.653953284676737e-06,
+      "loss": 0.4415,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7236662106703147,
+      "grad_norm": 1.2021058595481928,
+      "learning_rate": 4.574576797724984e-06,
+      "loss": 0.4161,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7373461012311902,
+      "grad_norm": 1.3115148564903278,
+      "learning_rate": 4.495308170066739e-06,
+      "loss": 0.4326,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7510259917920656,
+      "grad_norm": 1.2648526427702413,
+      "learning_rate": 4.4161674990030715e-06,
+      "loss": 0.4426,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 1.137931826008329,
+      "learning_rate": 4.3371748493936834e-06,
+      "loss": 0.4263,
+      "step": 1290
+    },
+    {
+      "epoch": 1.7783857729138166,
+      "grad_norm": 1.203799366153618,
+      "learning_rate": 4.2583502485697945e-06,
+      "loss": 0.422,
+      "step": 1300
+    },
+    {
+      "epoch": 1.792065663474692,
+      "grad_norm": 1.1215051415533788,
+      "learning_rate": 4.179713681256523e-06,
+      "loss": 0.4278,
+      "step": 1310
+    },
+    {
+      "epoch": 1.8057455540355676,
+      "grad_norm": 1.1919550892429331,
+      "learning_rate": 4.101285084506075e-06,
+      "loss": 0.4126,
+      "step": 1320
+    },
+    {
+      "epoch": 1.819425444596443,
+      "grad_norm": 1.2602652902830995,
+      "learning_rate": 4.023084342643026e-06,
+      "loss": 0.4302,
+      "step": 1330
+    },
+    {
+      "epoch": 1.8331053351573188,
+      "grad_norm": 1.1856280985422172,
+      "learning_rate": 3.94513128222297e-06,
+      "loss": 0.4308,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8467852257181943,
+      "grad_norm": 1.1188116484677932,
+      "learning_rate": 3.867445667005801e-06,
+      "loss": 0.4343,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8604651162790697,
+      "grad_norm": 1.1588258315903728,
+      "learning_rate": 3.790047192944931e-06,
+      "loss": 0.4301,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8741450068399452,
+      "grad_norm": 1.1459817706332724,
+      "learning_rate": 3.7129554831936998e-06,
+      "loss": 0.4175,
+      "step": 1370
+    },
+    {
+      "epoch": 1.887824897400821,
+      "grad_norm": 1.104555953617468,
+      "learning_rate": 3.6361900831302264e-06,
+      "loss": 0.4175,
+      "step": 1380
+    },
+    {
+      "epoch": 1.9015047879616964,
+      "grad_norm": 1.1942887584277926,
+      "learning_rate": 3.5597704554019907e-06,
+      "loss": 0.4211,
+      "step": 1390
+    },
+    {
+      "epoch": 1.915184678522572,
+      "grad_norm": 1.0668265437929074,
+      "learning_rate": 3.4837159749913944e-06,
+      "loss": 0.4195,
+      "step": 1400
+    },
+    {
+      "epoch": 1.915184678522572,
+      "eval_loss": 0.6006618142127991,
+      "eval_runtime": 167.6616,
+      "eval_samples_per_second": 31.003,
+      "eval_steps_per_second": 3.877,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9288645690834474,
+      "grad_norm": 1.088376315283852,
+      "learning_rate": 3.40804592430354e-06,
+      "loss": 0.4205,
+      "step": 1410
+    },
+    {
+      "epoch": 1.9425444596443229,
+      "grad_norm": 1.1227517978501422,
+      "learning_rate": 3.3327794882774785e-06,
+      "loss": 0.4295,
+      "step": 1420
+    },
+    {
+      "epoch": 1.9562243502051984,
+      "grad_norm": 1.1732094471787033,
+      "learning_rate": 3.2579357495221786e-06,
+      "loss": 0.4104,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9699042407660738,
+      "grad_norm": 1.2162059196521249,
+      "learning_rate": 3.183533683478427e-06,
+      "loss": 0.4091,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9835841313269493,
+      "grad_norm": 1.108696878534993,
+      "learning_rate": 3.1095921536079215e-06,
+      "loss": 0.43,
+      "step": 1450
+    },
+    {
+      "epoch": 1.9972640218878248,
+      "grad_norm": 1.148281960391559,
+      "learning_rate": 3.0361299066107225e-06,
+      "loss": 0.4146,
+      "step": 1460
+    },
+    {
+      "epoch": 2.0109439124487003,
+      "grad_norm": 1.853284154156804,
+      "learning_rate": 2.9631655676723358e-06,
+      "loss": 0.3057,
+      "step": 1470
+    },
+    {
+      "epoch": 2.024623803009576,
+      "grad_norm": 1.2698401561195134,
+      "learning_rate": 2.890717635741589e-06,
+      "loss": 0.2671,
+      "step": 1480
+    },
+    {
+      "epoch": 2.0383036935704513,
+      "grad_norm": 1.1953162644205662,
+      "learning_rate": 2.81880447884052e-06,
+      "loss": 0.2676,
+      "step": 1490
+    },
+    {
+      "epoch": 2.0519835841313268,
+      "grad_norm": 1.120927117498952,
+      "learning_rate": 2.7474443294074537e-06,
+      "loss": 0.2593,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0656634746922027,
+      "grad_norm": 1.324110443129841,
+      "learning_rate": 2.6766552796744583e-06,
+      "loss": 0.2703,
+      "step": 1510
+    },
+    {
+      "epoch": 2.079343365253078,
+      "grad_norm": 1.3413599300031922,
+      "learning_rate": 2.606455277080346e-06,
+      "loss": 0.2708,
+      "step": 1520
+    },
+    {
+      "epoch": 2.0930232558139537,
+      "grad_norm": 1.1788852376372527,
+      "learning_rate": 2.536862119720387e-06,
+      "loss": 0.2664,
+      "step": 1530
+    },
+    {
+      "epoch": 2.106703146374829,
+      "grad_norm": 1.1789132415176646,
+      "learning_rate": 2.467893451833884e-06,
+      "loss": 0.2673,
+      "step": 1540
+    },
+    {
+      "epoch": 2.1203830369357046,
+      "grad_norm": 1.2137095943380327,
+      "learning_rate": 2.3995667593307563e-06,
+      "loss": 0.2622,
+      "step": 1550
+    },
+    {
+      "epoch": 2.13406292749658,
+      "grad_norm": 1.2537108019590875,
+      "learning_rate": 2.331899365358266e-06,
+      "loss": 0.2695,
+      "step": 1560
+    },
+    {
+      "epoch": 2.1477428180574556,
+      "grad_norm": 1.2719182887175577,
+      "learning_rate": 2.2649084259090058e-06,
+      "loss": 0.2593,
+      "step": 1570
+    },
+    {
+      "epoch": 2.161422708618331,
+      "grad_norm": 1.164630355430247,
+      "learning_rate": 2.1986109254712745e-06,
+      "loss": 0.2708,
+      "step": 1580
+    },
+    {
+      "epoch": 2.1751025991792066,
+      "grad_norm": 1.1779155039946436,
+      "learning_rate": 2.133023672722923e-06,
+      "loss": 0.2697,
+      "step": 1590
+    },
+    {
+      "epoch": 2.188782489740082,
+      "grad_norm": 1.1294417346333414,
+      "learning_rate": 2.0681632962697955e-06,
+      "loss": 0.2528,
+      "step": 1600
+    },
+    {
+      "epoch": 2.188782489740082,
+      "eval_loss": 0.6378765106201172,
+      "eval_runtime": 171.4166,
+      "eval_samples_per_second": 30.324,
+      "eval_steps_per_second": 3.792,
+      "step": 1600
+    },
+    {
+      "epoch": 2.2024623803009575,
+      "grad_norm": 1.2183820949308963,
+      "learning_rate": 2.0040462404297873e-06,
+      "loss": 0.2719,
+      "step": 1610
+    },
+    {
+      "epoch": 2.216142270861833,
+      "grad_norm": 1.1698549285231044,
+      "learning_rate": 1.9406887610636716e-06,
+      "loss": 0.2659,
+      "step": 1620
+    },
+    {
+      "epoch": 2.2298221614227085,
+      "grad_norm": 1.2697486173216241,
+      "learning_rate": 1.8781069214536711e-06,
+      "loss": 0.2677,
+      "step": 1630
+    },
+    {
+      "epoch": 2.243502051983584,
+      "grad_norm": 1.214820822899955,
+      "learning_rate": 1.8163165882308776e-06,
+      "loss": 0.2662,
+      "step": 1640
+    },
+    {
+      "epoch": 2.2571819425444595,
+      "grad_norm": 1.3319711950469666,
+      "learning_rate": 1.7553334273525107e-06,
+      "loss": 0.2648,
+      "step": 1650
+    },
+    {
+      "epoch": 2.270861833105335,
+      "grad_norm": 1.245211504895954,
+      "learning_rate": 1.6951729001300626e-06,
+      "loss": 0.2659,
+      "step": 1660
+    },
+    {
+      "epoch": 2.2845417236662104,
+      "grad_norm": 1.2357536814491976,
+      "learning_rate": 1.6358502593093417e-06,
+      "loss": 0.2638,
+      "step": 1670
+    },
+    {
+      "epoch": 2.2982216142270864,
+      "grad_norm": 1.2488899759446517,
+      "learning_rate": 1.5773805452033664e-06,
+      "loss": 0.2647,
+      "step": 1680
+    },
+    {
+      "epoch": 2.311901504787962,
+      "grad_norm": 1.1504334028748302,
+      "learning_rate": 1.5197785818791395e-06,
+      "loss": 0.2611,
+      "step": 1690
+    },
+    {
+      "epoch": 2.3255813953488373,
+      "grad_norm": 1.2488245466965713,
+      "learning_rate": 1.463058973399241e-06,
+      "loss": 0.2597,
+      "step": 1700
+    },
+    {
+      "epoch": 2.339261285909713,
+      "grad_norm": 1.2329978043228385,
+      "learning_rate": 1.4072361001191997e-06,
+      "loss": 0.2664,
+      "step": 1710
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 1.200114038379274,
+      "learning_rate": 1.3523241150415822e-06,
+      "loss": 0.2579,
+      "step": 1720
+    },
+    {
+      "epoch": 2.366621067031464,
+      "grad_norm": 1.1866913191947843,
+      "learning_rate": 1.298336940227724e-06,
+      "loss": 0.2627,
+      "step": 1730
+    },
+    {
+      "epoch": 2.3803009575923393,
+      "grad_norm": 1.215070259088293,
+      "learning_rate": 1.2452882632680125e-06,
+      "loss": 0.2629,
+      "step": 1740
+    },
+    {
+      "epoch": 2.3939808481532148,
+      "grad_norm": 1.2848393192245922,
+      "learning_rate": 1.1931915338116157e-06,
+      "loss": 0.2579,
+      "step": 1750
+    },
+    {
+      "epoch": 2.4076607387140903,
+      "grad_norm": 1.178082536045285,
+      "learning_rate": 1.1420599601565375e-06,
+      "loss": 0.2655,
+      "step": 1760
+    },
+    {
+      "epoch": 2.4213406292749657,
+      "grad_norm": 1.1599349607603797,
+      "learning_rate": 1.0919065059008626e-06,
+      "loss": 0.2614,
+      "step": 1770
+    },
+    {
+      "epoch": 2.4350205198358412,
+      "grad_norm": 1.218569747775109,
+      "learning_rate": 1.042743886656043e-06,
+      "loss": 0.2633,
+      "step": 1780
+    },
+    {
+      "epoch": 2.4487004103967167,
+      "grad_norm": 1.1984843383370676,
+      "learning_rate": 9.94584566823062e-07,
+      "loss": 0.2626,
+      "step": 1790
+    },
+    {
+      "epoch": 2.462380300957592,
+      "grad_norm": 1.1483398440958268,
+      "learning_rate": 9.474407564322685e-07,
+      "loss": 0.2648,
+      "step": 1800
+    },
+    {
+      "epoch": 2.462380300957592,
+      "eval_loss": 0.6390905976295471,
+      "eval_runtime": 167.5515,
+      "eval_samples_per_second": 31.023,
+      "eval_steps_per_second": 3.879,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4760601915184677,
+      "grad_norm": 1.2020289928203793,
+      "learning_rate": 9.01324408047734e-07,
+      "loss": 0.2649,
+      "step": 1810
+    },
+    {
+      "epoch": 2.4897400820793436,
+      "grad_norm": 1.1514025291135426,
+      "learning_rate": 8.562472137368638e-07,
+      "loss": 0.2598,
+      "step": 1820
+    },
+    {
+      "epoch": 2.503419972640219,
+      "grad_norm": 1.1443562664564093,
+      "learning_rate": 8.122206021060552e-07,
+      "loss": 0.2627,
+      "step": 1830
+    },
+    {
+      "epoch": 2.5170998632010946,
+      "grad_norm": 1.2145886027335204,
+      "learning_rate": 7.692557354031633e-07,
+      "loss": 0.2554,
+      "step": 1840
+    },
+    {
+      "epoch": 2.53077975376197,
+      "grad_norm": 1.2003000862318016,
+      "learning_rate": 7.273635066874796e-07,
+      "loss": 0.2595,
+      "step": 1850
+    },
+    {
+      "epoch": 2.5444596443228455,
+      "grad_norm": 1.2102887918479095,
+      "learning_rate": 6.86554537067986e-07,
+      "loss": 0.2562,
+      "step": 1860
+    },
+    {
+      "epoch": 2.558139534883721,
+      "grad_norm": 1.1976060832616344,
+      "learning_rate": 6.46839173010525e-07,
+      "loss": 0.2589,
+      "step": 1870
+    },
+    {
+      "epoch": 2.5718194254445965,
+      "grad_norm": 1.1509734934067806,
+      "learning_rate": 6.08227483714629e-07,
+      "loss": 0.2565,
+      "step": 1880
+    },
+    {
+      "epoch": 2.585499316005472,
+      "grad_norm": 1.237509833168683,
+      "learning_rate": 5.707292585606277e-07,
+      "loss": 0.2646,
+      "step": 1890
+    },
+    {
+      "epoch": 2.5991792065663475,
+      "grad_norm": 1.2849404614912345,
+      "learning_rate": 5.343540046277113e-07,
+      "loss": 0.2571,
+      "step": 1900
+    },
+    {
+      "epoch": 2.612859097127223,
+      "grad_norm": 1.2020133789054372,
+      "learning_rate": 4.991109442835578e-07,
+      "loss": 0.2605,
+      "step": 1910
+    },
+    {
+      "epoch": 2.6265389876880985,
+      "grad_norm": 1.2567141981825356,
+      "learning_rate": 4.6500901284615094e-07,
+      "loss": 0.2621,
+      "step": 1920
+    },
+    {
+      "epoch": 2.640218878248974,
+      "grad_norm": 1.1549261891969707,
+      "learning_rate": 4.320568563183708e-07,
+      "loss": 0.2646,
+      "step": 1930
+    },
+    {
+      "epoch": 2.6538987688098494,
+      "grad_norm": 1.227541734725619,
+      "learning_rate": 4.0026282919593815e-07,
+      "loss": 0.2653,
+      "step": 1940
+    },
+    {
+      "epoch": 2.667578659370725,
+      "grad_norm": 1.1729506883600467,
+      "learning_rate": 3.6963499234926314e-07,
+      "loss": 0.2675,
+      "step": 1950
+    },
+    {
+      "epoch": 2.6812585499316004,
+      "grad_norm": 1.2392479528804268,
+      "learning_rate": 3.401811109797404e-07,
+      "loss": 0.2805,
+      "step": 1960
+    },
+    {
+      "epoch": 2.694938440492476,
+      "grad_norm": 1.1834886023051063,
+      "learning_rate": 3.1190865265100954e-07,
+      "loss": 0.2594,
+      "step": 1970
+    },
+    {
+      "epoch": 2.7086183310533514,
+      "grad_norm": 1.1342198262790109,
+      "learning_rate": 2.8482478539566595e-07,
+      "loss": 0.2662,
+      "step": 1980
+    },
+    {
+      "epoch": 2.722298221614227,
+      "grad_norm": 1.2035486656539252,
+      "learning_rate": 2.58936375897923e-07,
+      "loss": 0.2688,
+      "step": 1990
+    },
+    {
+      "epoch": 2.7359781121751023,
+      "grad_norm": 1.181326670816563,
+      "learning_rate": 2.342499877526755e-07,
+      "loss": 0.2586,
+      "step": 2000
+    },
+    {
+      "epoch": 2.7359781121751023,
+      "eval_loss": 0.6391583681106567,
+      "eval_runtime": 167.8571,
+      "eval_samples_per_second": 30.967,
+      "eval_steps_per_second": 3.872,
+      "step": 2000
+    },
+    {
+      "epoch": 2.7496580027359783,
+      "grad_norm": 1.1676009303739256,
+      "learning_rate": 2.1077187980140467e-07,
+      "loss": 0.2616,
+      "step": 2010
+    },
+    {
+      "epoch": 2.7633378932968538,
+      "grad_norm": 1.219603623890368,
+      "learning_rate": 1.8850800454534358e-07,
+      "loss": 0.2591,
+      "step": 2020
+    },
+    {
+      "epoch": 2.7770177838577292,
+      "grad_norm": 1.2643792382182215,
+      "learning_rate": 1.6746400663631923e-07,
+      "loss": 0.2608,
+      "step": 2030
+    },
+    {
+      "epoch": 2.7906976744186047,
+      "grad_norm": 1.2780674547136892,
+      "learning_rate": 1.4764522144563865e-07,
+      "loss": 0.2625,
+      "step": 2040
+    },
+    {
+      "epoch": 2.80437756497948,
+      "grad_norm": 1.2502610941549783,
+      "learning_rate": 1.2905667371139298e-07,
+      "loss": 0.259,
+      "step": 2050
+    },
+    {
+      "epoch": 2.8180574555403557,
+      "grad_norm": 1.246880298259785,
+      "learning_rate": 1.117030762645116e-07,
+      "loss": 0.2613,
+      "step": 2060
+    },
+    {
+      "epoch": 2.831737346101231,
+      "grad_norm": 1.2060582120323238,
+      "learning_rate": 9.558882883390075e-08,
+      "loss": 0.2607,
+      "step": 2070
+    },
+    {
+      "epoch": 2.8454172366621067,
+      "grad_norm": 1.1847791928318971,
+      "learning_rate": 8.071801693096237e-08,
+      "loss": 0.2575,
+      "step": 2080
+    },
+    {
+      "epoch": 2.859097127222982,
+      "grad_norm": 1.2366555323688222,
+      "learning_rate": 6.70944108137761e-08,
+      "loss": 0.2601,
+      "step": 2090
+    },
+    {
+      "epoch": 2.8727770177838576,
+      "grad_norm": 1.1353358354521152,
+      "learning_rate": 5.472146453121163e-08,
+      "loss": 0.2565,
+      "step": 2100
+    },
+    {
+      "epoch": 2.886456908344733,
+      "grad_norm": 1.2500960828119085,
+      "learning_rate": 4.360231504720813e-08,
+      "loss": 0.2726,
+      "step": 2110
+    },
+    {
+      "epoch": 2.9001367989056086,
+      "grad_norm": 1.234389078825029,
+      "learning_rate": 3.3739781445449316e-08,
+      "loss": 0.2544,
+      "step": 2120
+    },
+    {
+      "epoch": 2.9138166894664845,
+      "grad_norm": 1.1537121999523,
+      "learning_rate": 2.513636421462573e-08,
+      "loss": 0.2587,
+      "step": 2130
+    },
+    {
+      "epoch": 2.92749658002736,
+      "grad_norm": 1.1582097586418938,
+      "learning_rate": 1.779424461447965e-08,
+      "loss": 0.2622,
+      "step": 2140
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 1.1715551395170911,
+      "learning_rate": 1.1715284122779114e-08,
+      "loss": 0.261,
+      "step": 2150
+    },
+    {
+      "epoch": 2.954856361149111,
+      "grad_norm": 1.14493606362213,
+      "learning_rate": 6.901023963369336e-09,
+      "loss": 0.2581,
+      "step": 2160
+    },
+    {
+      "epoch": 2.9685362517099865,
+      "grad_norm": 1.2230232820768532,
+      "learning_rate": 3.3526847154219387e-09,
+      "loss": 0.2577,
+      "step": 2170
+    },
+    {
+      "epoch": 2.982216142270862,
+      "grad_norm": 1.2703211507866685,
+      "learning_rate": 1.0711660039747219e-09,
+      "loss": 0.2691,
+      "step": 2180
+    },
+    {
+      "epoch": 2.9958960328317374,
+      "grad_norm": 1.1271004957793302,
+      "learning_rate": 5.704627184577316e-11,
+      "loss": 0.2604,
+      "step": 2190
+    },
+    {
+      "epoch": 3.0,
+      "step": 2193,
+      "total_flos": 391576352194560.0,
+      "train_loss": 0.44177393167463547,
+      "train_runtime": 22000.6442,
+      "train_samples_per_second": 6.378,
+      "train_steps_per_second": 0.1
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2193,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 391576352194560.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9388ad5a3fc13843546dca7399d1725b9528d611ee2fd11e5f9458b1bf04def
+size 7160