Upload folder using huggingface_hub

.gitattributes

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

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/workspace/data/gemma-2-9b-chatml",
+  "architectures": [
+    "Gemma2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": 50.0,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 8,
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 42,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "sliding_window_size": 4096,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": 8,
+  "pad_token_id": 0,
+  "transformers_version": "4.45.0.dev0"
+}

latest

@@ -0,0 +1 @@
+global_step376

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:948fc034ea14d71c090aeb2d5a130fb36fa90da2f19890187d8b3200504ec934
+size 4903351912

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b83db132fab9b731f76f748ac85242de686a457f0a1319f151bf55b35451d0
+size 4947570872

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a478a2d2423b1f1b28126cf78c91ced479ad08a4d8b93dff4da3f9b8f5e95ad
+size 4962221464

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e93c2aeae05367c304fd270bf1ffada8de694f37771052d85ec6af12bcb98b6
+size 3670322200

model.safetensors.index.json

@@ -0,0 +1,471 @@
+{
+  "metadata": {
+    "total_size": 18483411968
+  },
+  "weight_map": {
+    "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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.pre_feedforward_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-00003-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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00004-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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.pre_feedforward_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.40.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00004-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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.pre_feedforward_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-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.pre_feedforward_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 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7d2783779c7a0fcbff8931e552ed350f4462104b30708eb4e72a7105b48dc1
+size 17518532

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f545c6099874ce0c5cf6e4ccecd5f2bce689852b576ddf9d49134081c9cb98
+size 4241007

tokenizer_config.json

@@ -0,0 +1,1757 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,2665 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9980092899800929,
+  "eval_steps": 500,
+  "global_step": 376,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0026542800265428003,
+      "grad_norm": 6.981875026564461,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.5142,
+      "step": 1
+    },
+    {
+      "epoch": 0.0053085600530856005,
+      "grad_norm": 7.3585790096388095,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.5399,
+      "step": 2
+    },
+    {
+      "epoch": 0.007962840079628402,
+      "grad_norm": 6.187456707748293,
+      "learning_rate": 3e-06,
+      "loss": 1.4331,
+      "step": 3
+    },
+    {
+      "epoch": 0.010617120106171201,
+      "grad_norm": 3.322201654326747,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.4069,
+      "step": 4
+    },
+    {
+      "epoch": 0.013271400132714002,
+      "grad_norm": 6.898750176066953,
+      "learning_rate": 5e-06,
+      "loss": 1.398,
+      "step": 5
+    },
+    {
+      "epoch": 0.015925680159256803,
+      "grad_norm": 9.84996090672252,
+      "learning_rate": 6e-06,
+      "loss": 1.4207,
+      "step": 6
+    },
+    {
+      "epoch": 0.0185799601857996,
+      "grad_norm": 5.911295227152632,
+      "learning_rate": 7e-06,
+      "loss": 1.396,
+      "step": 7
+    },
+    {
+      "epoch": 0.021234240212342402,
+      "grad_norm": 4.487244776192921,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.3842,
+      "step": 8
+    },
+    {
+      "epoch": 0.023888520238885203,
+      "grad_norm": 3.963029697998983,
+      "learning_rate": 9e-06,
+      "loss": 1.4094,
+      "step": 9
+    },
+    {
+      "epoch": 0.026542800265428004,
+      "grad_norm": 3.9061159778838777,
+      "learning_rate": 1e-05,
+      "loss": 1.3289,
+      "step": 10
+    },
+    {
+      "epoch": 0.029197080291970802,
+      "grad_norm": 4.06704445096823,
+      "learning_rate": 9.999988945517944e-06,
+      "loss": 1.3803,
+      "step": 11
+    },
+    {
+      "epoch": 0.03185136031851361,
+      "grad_norm": 2.604059841393431,
+      "learning_rate": 9.999955782120656e-06,
+      "loss": 1.3673,
+      "step": 12
+    },
+    {
+      "epoch": 0.034505640345056404,
+      "grad_norm": 2.257369986938731,
+      "learning_rate": 9.999900509954779e-06,
+      "loss": 1.3601,
+      "step": 13
+    },
+    {
+      "epoch": 0.0371599203715992,
+      "grad_norm": 2.1847487718443896,
+      "learning_rate": 9.999823129264712e-06,
+      "loss": 1.2897,
+      "step": 14
+    },
+    {
+      "epoch": 0.039814200398142006,
+      "grad_norm": 2.07192636064569,
+      "learning_rate": 9.99972364039262e-06,
+      "loss": 1.3908,
+      "step": 15
+    },
+    {
+      "epoch": 0.042468480424684804,
+      "grad_norm": 1.9501283234498499,
+      "learning_rate": 9.99960204377842e-06,
+      "loss": 1.3159,
+      "step": 16
+    },
+    {
+      "epoch": 0.0451227604512276,
+      "grad_norm": 2.493269875780714,
+      "learning_rate": 9.999458339959787e-06,
+      "loss": 1.294,
+      "step": 17
+    },
+    {
+      "epoch": 0.047777040477770406,
+      "grad_norm": 2.5949272964482057,
+      "learning_rate": 9.999292529572152e-06,
+      "loss": 1.3185,
+      "step": 18
+    },
+    {
+      "epoch": 0.050431320504313204,
+      "grad_norm": 2.2388099180255643,
+      "learning_rate": 9.99910461334869e-06,
+      "loss": 1.2132,
+      "step": 19
+    },
+    {
+      "epoch": 0.05308560053085601,
+      "grad_norm": 2.2899507956205762,
+      "learning_rate": 9.99889459212033e-06,
+      "loss": 1.293,
+      "step": 20
+    },
+    {
+      "epoch": 0.055739880557398806,
+      "grad_norm": 1.9172996859984803,
+      "learning_rate": 9.998662466815743e-06,
+      "loss": 1.2282,
+      "step": 21
+    },
+    {
+      "epoch": 0.058394160583941604,
+      "grad_norm": 1.695255684950505,
+      "learning_rate": 9.99840823846134e-06,
+      "loss": 1.2453,
+      "step": 22
+    },
+    {
+      "epoch": 0.06104844061048441,
+      "grad_norm": 1.9499380269432547,
+      "learning_rate": 9.998131908181262e-06,
+      "loss": 1.3126,
+      "step": 23
+    },
+    {
+      "epoch": 0.06370272063702721,
+      "grad_norm": 2.235039095134041,
+      "learning_rate": 9.997833477197386e-06,
+      "loss": 1.3,
+      "step": 24
+    },
+    {
+      "epoch": 0.06635700066357,
+      "grad_norm": 1.7768874556246268,
+      "learning_rate": 9.997512946829314e-06,
+      "loss": 1.3027,
+      "step": 25
+    },
+    {
+      "epoch": 0.06901128069011281,
+      "grad_norm": 1.8710962469378072,
+      "learning_rate": 9.997170318494362e-06,
+      "loss": 1.2571,
+      "step": 26
+    },
+    {
+      "epoch": 0.07166556071665561,
+      "grad_norm": 2.1786369089634734,
+      "learning_rate": 9.996805593707566e-06,
+      "loss": 1.2633,
+      "step": 27
+    },
+    {
+      "epoch": 0.0743198407431984,
+      "grad_norm": 2.3145346512057805,
+      "learning_rate": 9.996418774081658e-06,
+      "loss": 1.2439,
+      "step": 28
+    },
+    {
+      "epoch": 0.07697412076974121,
+      "grad_norm": 1.740845781272116,
+      "learning_rate": 9.996009861327077e-06,
+      "loss": 1.2437,
+      "step": 29
+    },
+    {
+      "epoch": 0.07962840079628401,
+      "grad_norm": 1.9183185283288997,
+      "learning_rate": 9.99557885725195e-06,
+      "loss": 1.333,
+      "step": 30
+    },
+    {
+      "epoch": 0.0822826808228268,
+      "grad_norm": 2.1688553875791987,
+      "learning_rate": 9.995125763762089e-06,
+      "loss": 1.3145,
+      "step": 31
+    },
+    {
+      "epoch": 0.08493696084936961,
+      "grad_norm": 1.9658120398634014,
+      "learning_rate": 9.994650582860978e-06,
+      "loss": 1.2682,
+      "step": 32
+    },
+    {
+      "epoch": 0.08759124087591241,
+      "grad_norm": 2.136505316782775,
+      "learning_rate": 9.994153316649769e-06,
+      "loss": 1.24,
+      "step": 33
+    },
+    {
+      "epoch": 0.0902455209024552,
+      "grad_norm": 1.670383957571605,
+      "learning_rate": 9.99363396732727e-06,
+      "loss": 1.2421,
+      "step": 34
+    },
+    {
+      "epoch": 0.09289980092899801,
+      "grad_norm": 1.9007693724974954,
+      "learning_rate": 9.993092537189936e-06,
+      "loss": 1.1936,
+      "step": 35
+    },
+    {
+      "epoch": 0.09555408095554081,
+      "grad_norm": 1.8427231589681057,
+      "learning_rate": 9.992529028631859e-06,
+      "loss": 1.2568,
+      "step": 36
+    },
+    {
+      "epoch": 0.0982083609820836,
+      "grad_norm": 1.9014135968523682,
+      "learning_rate": 9.991943444144758e-06,
+      "loss": 1.231,
+      "step": 37
+    },
+    {
+      "epoch": 0.10086264100862641,
+      "grad_norm": 1.714724530777744,
+      "learning_rate": 9.991335786317964e-06,
+      "loss": 1.2559,
+      "step": 38
+    },
+    {
+      "epoch": 0.10351692103516921,
+      "grad_norm": 1.9540837660082362,
+      "learning_rate": 9.990706057838417e-06,
+      "loss": 1.2583,
+      "step": 39
+    },
+    {
+      "epoch": 0.10617120106171202,
+      "grad_norm": 1.7120831927587263,
+      "learning_rate": 9.990054261490643e-06,
+      "loss": 1.2095,
+      "step": 40
+    },
+    {
+      "epoch": 0.10882548108825481,
+      "grad_norm": 1.7124302876215762,
+      "learning_rate": 9.989380400156752e-06,
+      "loss": 1.2361,
+      "step": 41
+    },
+    {
+      "epoch": 0.11147976111479761,
+      "grad_norm": 1.7683889355402804,
+      "learning_rate": 9.98868447681642e-06,
+      "loss": 1.2134,
+      "step": 42
+    },
+    {
+      "epoch": 0.11413404114134042,
+      "grad_norm": 1.8716677445605339,
+      "learning_rate": 9.987966494546873e-06,
+      "loss": 1.3081,
+      "step": 43
+    },
+    {
+      "epoch": 0.11678832116788321,
+      "grad_norm": 1.810504125507985,
+      "learning_rate": 9.987226456522884e-06,
+      "loss": 1.2789,
+      "step": 44
+    },
+    {
+      "epoch": 0.11944260119442601,
+      "grad_norm": 2.107999452852097,
+      "learning_rate": 9.986464366016743e-06,
+      "loss": 1.2965,
+      "step": 45
+    },
+    {
+      "epoch": 0.12209688122096882,
+      "grad_norm": 1.9463843496195974,
+      "learning_rate": 9.985680226398261e-06,
+      "loss": 1.2455,
+      "step": 46
+    },
+    {
+      "epoch": 0.12475116124751161,
+      "grad_norm": 1.8557616158057193,
+      "learning_rate": 9.984874041134738e-06,
+      "loss": 1.2432,
+      "step": 47
+    },
+    {
+      "epoch": 0.12740544127405443,
+      "grad_norm": 1.7060682110649106,
+      "learning_rate": 9.984045813790959e-06,
+      "loss": 1.1864,
+      "step": 48
+    },
+    {
+      "epoch": 0.1300597213005972,
+      "grad_norm": 1.9204675247056242,
+      "learning_rate": 9.983195548029173e-06,
+      "loss": 1.2525,
+      "step": 49
+    },
+    {
+      "epoch": 0.13271400132714,
+      "grad_norm": 1.8711916549013854,
+      "learning_rate": 9.98232324760908e-06,
+      "loss": 1.2836,
+      "step": 50
+    },
+    {
+      "epoch": 0.1353682813536828,
+      "grad_norm": 1.6842894937517436,
+      "learning_rate": 9.981428916387812e-06,
+      "loss": 1.183,
+      "step": 51
+    },
+    {
+      "epoch": 0.13802256138022562,
+      "grad_norm": 1.6306230130296617,
+      "learning_rate": 9.980512558319915e-06,
+      "loss": 1.2369,
+      "step": 52
+    },
+    {
+      "epoch": 0.14067684140676842,
+      "grad_norm": 1.566857719000752,
+      "learning_rate": 9.979574177457337e-06,
+      "loss": 1.1844,
+      "step": 53
+    },
+    {
+      "epoch": 0.14333112143331123,
+      "grad_norm": 2.0361026967903966,
+      "learning_rate": 9.978613777949401e-06,
+      "loss": 1.2064,
+      "step": 54
+    },
+    {
+      "epoch": 0.145985401459854,
+      "grad_norm": 1.8265620367248863,
+      "learning_rate": 9.977631364042796e-06,
+      "loss": 1.2432,
+      "step": 55
+    },
+    {
+      "epoch": 0.1486396814863968,
+      "grad_norm": 1.7838441388683621,
+      "learning_rate": 9.976626940081553e-06,
+      "loss": 1.2852,
+      "step": 56
+    },
+    {
+      "epoch": 0.1512939615129396,
+      "grad_norm": 1.7544005767854343,
+      "learning_rate": 9.975600510507025e-06,
+      "loss": 1.1735,
+      "step": 57
+    },
+    {
+      "epoch": 0.15394824153948242,
+      "grad_norm": 1.80732471729061,
+      "learning_rate": 9.974552079857873e-06,
+      "loss": 1.2198,
+      "step": 58
+    },
+    {
+      "epoch": 0.15660252156602522,
+      "grad_norm": 1.7204547120415132,
+      "learning_rate": 9.973481652770039e-06,
+      "loss": 1.2409,
+      "step": 59
+    },
+    {
+      "epoch": 0.15925680159256803,
+      "grad_norm": 1.7446267682486616,
+      "learning_rate": 9.972389233976729e-06,
+      "loss": 1.236,
+      "step": 60
+    },
+    {
+      "epoch": 0.1619110816191108,
+      "grad_norm": 1.8367615413386507,
+      "learning_rate": 9.971274828308396e-06,
+      "loss": 1.2333,
+      "step": 61
+    },
+    {
+      "epoch": 0.1645653616456536,
+      "grad_norm": 2.024298503175875,
+      "learning_rate": 9.970138440692706e-06,
+      "loss": 1.1798,
+      "step": 62
+    },
+    {
+      "epoch": 0.1672196416721964,
+      "grad_norm": 1.6639343310164172,
+      "learning_rate": 9.968980076154533e-06,
+      "loss": 1.2429,
+      "step": 63
+    },
+    {
+      "epoch": 0.16987392169873922,
+      "grad_norm": 1.7526879469365466,
+      "learning_rate": 9.967799739815925e-06,
+      "loss": 1.2448,
+      "step": 64
+    },
+    {
+      "epoch": 0.17252820172528202,
+      "grad_norm": 1.551089471898675,
+      "learning_rate": 9.966597436896085e-06,
+      "loss": 1.2221,
+      "step": 65
+    },
+    {
+      "epoch": 0.17518248175182483,
+      "grad_norm": 3.285115069392907,
+      "learning_rate": 9.965373172711343e-06,
+      "loss": 1.2576,
+      "step": 66
+    },
+    {
+      "epoch": 0.17783676177836763,
+      "grad_norm": 1.9429706042692902,
+      "learning_rate": 9.964126952675148e-06,
+      "loss": 1.2211,
+      "step": 67
+    },
+    {
+      "epoch": 0.1804910418049104,
+      "grad_norm": 1.6014290221743892,
+      "learning_rate": 9.962858782298023e-06,
+      "loss": 1.2105,
+      "step": 68
+    },
+    {
+      "epoch": 0.1831453218314532,
+      "grad_norm": 1.7597646377706344,
+      "learning_rate": 9.961568667187556e-06,
+      "loss": 1.2401,
+      "step": 69
+    },
+    {
+      "epoch": 0.18579960185799602,
+      "grad_norm": 1.6408652164338016,
+      "learning_rate": 9.960256613048367e-06,
+      "loss": 1.1577,
+      "step": 70
+    },
+    {
+      "epoch": 0.18845388188453882,
+      "grad_norm": 2.4349687274686334,
+      "learning_rate": 9.958922625682088e-06,
+      "loss": 1.193,
+      "step": 71
+    },
+    {
+      "epoch": 0.19110816191108163,
+      "grad_norm": 1.9037201335080784,
+      "learning_rate": 9.957566710987338e-06,
+      "loss": 1.1489,
+      "step": 72
+    },
+    {
+      "epoch": 0.19376244193762443,
+      "grad_norm": 2.1368452991743014,
+      "learning_rate": 9.956188874959686e-06,
+      "loss": 1.3215,
+      "step": 73
+    },
+    {
+      "epoch": 0.1964167219641672,
+      "grad_norm": 1.7342842074642177,
+      "learning_rate": 9.954789123691643e-06,
+      "loss": 1.2288,
+      "step": 74
+    },
+    {
+      "epoch": 0.19907100199071,
+      "grad_norm": 1.883985974459675,
+      "learning_rate": 9.953367463372615e-06,
+      "loss": 1.2349,
+      "step": 75
+    },
+    {
+      "epoch": 0.20172528201725282,
+      "grad_norm": 1.8151478617151462,
+      "learning_rate": 9.951923900288888e-06,
+      "loss": 1.1481,
+      "step": 76
+    },
+    {
+      "epoch": 0.20437956204379562,
+      "grad_norm": 1.8542475078063598,
+      "learning_rate": 9.950458440823602e-06,
+      "loss": 1.262,
+      "step": 77
+    },
+    {
+      "epoch": 0.20703384207033843,
+      "grad_norm": 1.77553753540162,
+      "learning_rate": 9.948971091456715e-06,
+      "loss": 1.1834,
+      "step": 78
+    },
+    {
+      "epoch": 0.20968812209688123,
+      "grad_norm": 1.8152497279053155,
+      "learning_rate": 9.947461858764978e-06,
+      "loss": 1.1749,
+      "step": 79
+    },
+    {
+      "epoch": 0.21234240212342403,
+      "grad_norm": 1.5929993680573362,
+      "learning_rate": 9.945930749421903e-06,
+      "loss": 1.2696,
+      "step": 80
+    },
+    {
+      "epoch": 0.2149966821499668,
+      "grad_norm": 2.1883175245684092,
+      "learning_rate": 9.944377770197741e-06,
+      "loss": 1.2375,
+      "step": 81
+    },
+    {
+      "epoch": 0.21765096217650962,
+      "grad_norm": 1.7556050567556294,
+      "learning_rate": 9.942802927959444e-06,
+      "loss": 1.2017,
+      "step": 82
+    },
+    {
+      "epoch": 0.22030524220305242,
+      "grad_norm": 1.7392066404895135,
+      "learning_rate": 9.941206229670634e-06,
+      "loss": 1.1788,
+      "step": 83
+    },
+    {
+      "epoch": 0.22295952222959523,
+      "grad_norm": 2.230563622877349,
+      "learning_rate": 9.939587682391587e-06,
+      "loss": 1.2629,
+      "step": 84
+    },
+    {
+      "epoch": 0.22561380225613803,
+      "grad_norm": 1.7257531276366218,
+      "learning_rate": 9.937947293279178e-06,
+      "loss": 1.1574,
+      "step": 85
+    },
+    {
+      "epoch": 0.22826808228268083,
+      "grad_norm": 3.7946522494948134,
+      "learning_rate": 9.93628506958687e-06,
+      "loss": 1.2539,
+      "step": 86
+    },
+    {
+      "epoch": 0.2309223623092236,
+      "grad_norm": 1.7746755901383093,
+      "learning_rate": 9.934601018664672e-06,
+      "loss": 1.1672,
+      "step": 87
+    },
+    {
+      "epoch": 0.23357664233576642,
+      "grad_norm": 1.6160184542663385,
+      "learning_rate": 9.932895147959106e-06,
+      "loss": 1.2047,
+      "step": 88
+    },
+    {
+      "epoch": 0.23623092236230922,
+      "grad_norm": 1.597818533914632,
+      "learning_rate": 9.931167465013182e-06,
+      "loss": 1.2087,
+      "step": 89
+    },
+    {
+      "epoch": 0.23888520238885202,
+      "grad_norm": 1.8200709191179871,
+      "learning_rate": 9.929417977466356e-06,
+      "loss": 1.2594,
+      "step": 90
+    },
+    {
+      "epoch": 0.24153948241539483,
+      "grad_norm": 1.5869876859286098,
+      "learning_rate": 9.927646693054498e-06,
+      "loss": 1.2923,
+      "step": 91
+    },
+    {
+      "epoch": 0.24419376244193763,
+      "grad_norm": 1.6678230174198274,
+      "learning_rate": 9.925853619609858e-06,
+      "loss": 1.1979,
+      "step": 92
+    },
+    {
+      "epoch": 0.2468480424684804,
+      "grad_norm": 1.7206885835934083,
+      "learning_rate": 9.924038765061042e-06,
+      "loss": 1.2248,
+      "step": 93
+    },
+    {
+      "epoch": 0.24950232249502322,
+      "grad_norm": 1.8965216866987153,
+      "learning_rate": 9.922202137432954e-06,
+      "loss": 1.1793,
+      "step": 94
+    },
+    {
+      "epoch": 0.252156602521566,
+      "grad_norm": 1.7827181222199764,
+      "learning_rate": 9.920343744846786e-06,
+      "loss": 1.2539,
+      "step": 95
+    },
+    {
+      "epoch": 0.25481088254810885,
+      "grad_norm": 1.704509646049322,
+      "learning_rate": 9.918463595519963e-06,
+      "loss": 1.1845,
+      "step": 96
+    },
+    {
+      "epoch": 0.25746516257465163,
+      "grad_norm": 1.8008684596562938,
+      "learning_rate": 9.916561697766114e-06,
+      "loss": 1.1873,
+      "step": 97
+    },
+    {
+      "epoch": 0.2601194426011944,
+      "grad_norm": 1.5268474470110187,
+      "learning_rate": 9.91463805999504e-06,
+      "loss": 1.1634,
+      "step": 98
+    },
+    {
+      "epoch": 0.26277372262773724,
+      "grad_norm": 1.69776670129652,
+      "learning_rate": 9.912692690712667e-06,
+      "loss": 1.2496,
+      "step": 99
+    },
+    {
+      "epoch": 0.26542800265428,
+      "grad_norm": 19.950768938401303,
+      "learning_rate": 9.910725598521014e-06,
+      "loss": 1.2266,
+      "step": 100
+    },
+    {
+      "epoch": 0.26808228268082285,
+      "grad_norm": 1.888189833523382,
+      "learning_rate": 9.908736792118157e-06,
+      "loss": 1.1783,
+      "step": 101
+    },
+    {
+      "epoch": 0.2707365627073656,
+      "grad_norm": 1.6553587447766995,
+      "learning_rate": 9.906726280298185e-06,
+      "loss": 1.1888,
+      "step": 102
+    },
+    {
+      "epoch": 0.2733908427339084,
+      "grad_norm": 1.7645503651144456,
+      "learning_rate": 9.904694071951167e-06,
+      "loss": 1.2331,
+      "step": 103
+    },
+    {
+      "epoch": 0.27604512276045123,
+      "grad_norm": 1.7561319773931536,
+      "learning_rate": 9.902640176063103e-06,
+      "loss": 1.2429,
+      "step": 104
+    },
+    {
+      "epoch": 0.278699402786994,
+      "grad_norm": 1.826781329048666,
+      "learning_rate": 9.900564601715898e-06,
+      "loss": 1.2053,
+      "step": 105
+    },
+    {
+      "epoch": 0.28135368281353684,
+      "grad_norm": 2.0178364653670777,
+      "learning_rate": 9.89846735808731e-06,
+      "loss": 1.1855,
+      "step": 106
+    },
+    {
+      "epoch": 0.2840079628400796,
+      "grad_norm": 2.1853732110604027,
+      "learning_rate": 9.896348454450918e-06,
+      "loss": 1.1514,
+      "step": 107
+    },
+    {
+      "epoch": 0.28666224286662245,
+      "grad_norm": 1.863102490412834,
+      "learning_rate": 9.894207900176074e-06,
+      "loss": 1.1582,
+      "step": 108
+    },
+    {
+      "epoch": 0.28931652289316523,
+      "grad_norm": 2.1558166021806504,
+      "learning_rate": 9.892045704727864e-06,
+      "loss": 1.2692,
+      "step": 109
+    },
+    {
+      "epoch": 0.291970802919708,
+      "grad_norm": 1.623855596114215,
+      "learning_rate": 9.889861877667071e-06,
+      "loss": 1.1406,
+      "step": 110
+    },
+    {
+      "epoch": 0.29462508294625084,
+      "grad_norm": 1.925359975573577,
+      "learning_rate": 9.887656428650123e-06,
+      "loss": 1.144,
+      "step": 111
+    },
+    {
+      "epoch": 0.2972793629727936,
+      "grad_norm": 2.0780064875742634,
+      "learning_rate": 9.885429367429062e-06,
+      "loss": 1.2095,
+      "step": 112
+    },
+    {
+      "epoch": 0.29993364299933645,
+      "grad_norm": 1.757836459981376,
+      "learning_rate": 9.883180703851488e-06,
+      "loss": 1.2129,
+      "step": 113
+    },
+    {
+      "epoch": 0.3025879230258792,
+      "grad_norm": 1.6497771335719753,
+      "learning_rate": 9.880910447860527e-06,
+      "loss": 1.1528,
+      "step": 114
+    },
+    {
+      "epoch": 0.30524220305242206,
+      "grad_norm": 1.9314161378924497,
+      "learning_rate": 9.878618609494781e-06,
+      "loss": 1.2038,
+      "step": 115
+    },
+    {
+      "epoch": 0.30789648307896483,
+      "grad_norm": 1.5945997988558909,
+      "learning_rate": 9.876305198888284e-06,
+      "loss": 1.1349,
+      "step": 116
+    },
+    {
+      "epoch": 0.3105507631055076,
+      "grad_norm": 1.7095400428823162,
+      "learning_rate": 9.873970226270458e-06,
+      "loss": 1.1543,
+      "step": 117
+    },
+    {
+      "epoch": 0.31320504313205044,
+      "grad_norm": 1.6150384960254696,
+      "learning_rate": 9.871613701966067e-06,
+      "loss": 1.1527,
+      "step": 118
+    },
+    {
+      "epoch": 0.3158593231585932,
+      "grad_norm": 3.288441610824325,
+      "learning_rate": 9.869235636395177e-06,
+      "loss": 1.2411,
+      "step": 119
+    },
+    {
+      "epoch": 0.31851360318513605,
+      "grad_norm": 1.6258023683537948,
+      "learning_rate": 9.866836040073099e-06,
+      "loss": 1.2002,
+      "step": 120
+    },
+    {
+      "epoch": 0.32116788321167883,
+      "grad_norm": 1.6467592688369062,
+      "learning_rate": 9.86441492361035e-06,
+      "loss": 1.2134,
+      "step": 121
+    },
+    {
+      "epoch": 0.3238221632382216,
+      "grad_norm": 1.5988307616959179,
+      "learning_rate": 9.861972297712606e-06,
+      "loss": 1.2259,
+      "step": 122
+    },
+    {
+      "epoch": 0.32647644326476444,
+      "grad_norm": 1.9915164437167947,
+      "learning_rate": 9.859508173180653e-06,
+      "loss": 1.2369,
+      "step": 123
+    },
+    {
+      "epoch": 0.3291307232913072,
+      "grad_norm": 1.751874113048822,
+      "learning_rate": 9.857022560910338e-06,
+      "loss": 1.1954,
+      "step": 124
+    },
+    {
+      "epoch": 0.33178500331785005,
+      "grad_norm": 1.589249974809787,
+      "learning_rate": 9.854515471892527e-06,
+      "loss": 1.1434,
+      "step": 125
+    },
+    {
+      "epoch": 0.3344392833443928,
+      "grad_norm": 1.6571603039493696,
+      "learning_rate": 9.851986917213044e-06,
+      "loss": 1.1276,
+      "step": 126
+    },
+    {
+      "epoch": 0.33709356337093566,
+      "grad_norm": 1.821753338127428,
+      "learning_rate": 9.849436908052636e-06,
+      "loss": 1.1889,
+      "step": 127
+    },
+    {
+      "epoch": 0.33974784339747843,
+      "grad_norm": 1.55634782143693,
+      "learning_rate": 9.846865455686915e-06,
+      "loss": 1.1833,
+      "step": 128
+    },
+    {
+      "epoch": 0.3424021234240212,
+      "grad_norm": 1.4585503339043484,
+      "learning_rate": 9.844272571486313e-06,
+      "loss": 1.1979,
+      "step": 129
+    },
+    {
+      "epoch": 0.34505640345056404,
+      "grad_norm": 1.6155812940652678,
+      "learning_rate": 9.84165826691602e-06,
+      "loss": 1.179,
+      "step": 130
+    },
+    {
+      "epoch": 0.3477106834771068,
+      "grad_norm": 1.609059975302855,
+      "learning_rate": 9.839022553535957e-06,
+      "loss": 1.2091,
+      "step": 131
+    },
+    {
+      "epoch": 0.35036496350364965,
+      "grad_norm": 1.6996931072095949,
+      "learning_rate": 9.836365443000697e-06,
+      "loss": 1.1223,
+      "step": 132
+    },
+    {
+      "epoch": 0.35301924353019243,
+      "grad_norm": 1.616355220759201,
+      "learning_rate": 9.833686947059436e-06,
+      "loss": 1.0918,
+      "step": 133
+    },
+    {
+      "epoch": 0.35567352355673526,
+      "grad_norm": 1.6096571582268207,
+      "learning_rate": 9.830987077555925e-06,
+      "loss": 1.1654,
+      "step": 134
+    },
+    {
+      "epoch": 0.35832780358327804,
+      "grad_norm": 1.565339921018465,
+      "learning_rate": 9.828265846428428e-06,
+      "loss": 1.1634,
+      "step": 135
+    },
+    {
+      "epoch": 0.3609820836098208,
+      "grad_norm": 1.546016830156871,
+      "learning_rate": 9.825523265709667e-06,
+      "loss": 1.1751,
+      "step": 136
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 2.0425258490960836,
+      "learning_rate": 9.822759347526766e-06,
+      "loss": 1.1841,
+      "step": 137
+    },
+    {
+      "epoch": 0.3662906436629064,
+      "grad_norm": 1.7147276492095496,
+      "learning_rate": 9.819974104101198e-06,
+      "loss": 1.2335,
+      "step": 138
+    },
+    {
+      "epoch": 0.36894492368944926,
+      "grad_norm": 1.5869898030324339,
+      "learning_rate": 9.817167547748729e-06,
+      "loss": 1.2584,
+      "step": 139
+    },
+    {
+      "epoch": 0.37159920371599203,
+      "grad_norm": 1.6478179096824475,
+      "learning_rate": 9.814339690879376e-06,
+      "loss": 1.1961,
+      "step": 140
+    },
+    {
+      "epoch": 0.37425348374253486,
+      "grad_norm": 1.5596319041645448,
+      "learning_rate": 9.811490545997331e-06,
+      "loss": 1.2046,
+      "step": 141
+    },
+    {
+      "epoch": 0.37690776376907764,
+      "grad_norm": 1.81548347845434,
+      "learning_rate": 9.808620125700925e-06,
+      "loss": 1.2137,
+      "step": 142
+    },
+    {
+      "epoch": 0.3795620437956204,
+      "grad_norm": 1.5700607431043994,
+      "learning_rate": 9.80572844268256e-06,
+      "loss": 1.2,
+      "step": 143
+    },
+    {
+      "epoch": 0.38221632382216325,
+      "grad_norm": 1.6383722320139935,
+      "learning_rate": 9.802815509728662e-06,
+      "loss": 1.1747,
+      "step": 144
+    },
+    {
+      "epoch": 0.384870603848706,
+      "grad_norm": 1.8125605110455933,
+      "learning_rate": 9.799881339719615e-06,
+      "loss": 1.1867,
+      "step": 145
+    },
+    {
+      "epoch": 0.38752488387524886,
+      "grad_norm": 1.7582804382886328,
+      "learning_rate": 9.796925945629711e-06,
+      "loss": 1.3162,
+      "step": 146
+    },
+    {
+      "epoch": 0.39017916390179164,
+      "grad_norm": 2.0734414221603665,
+      "learning_rate": 9.793949340527091e-06,
+      "loss": 1.234,
+      "step": 147
+    },
+    {
+      "epoch": 0.3928334439283344,
+      "grad_norm": 1.5379766795331946,
+      "learning_rate": 9.790951537573686e-06,
+      "loss": 1.1185,
+      "step": 148
+    },
+    {
+      "epoch": 0.39548772395487725,
+      "grad_norm": 1.6227118631483388,
+      "learning_rate": 9.787932550025158e-06,
+      "loss": 1.1523,
+      "step": 149
+    },
+    {
+      "epoch": 0.39814200398142,
+      "grad_norm": 1.5530246573576652,
+      "learning_rate": 9.784892391230847e-06,
+      "loss": 1.1405,
+      "step": 150
+    },
+    {
+      "epoch": 0.40079628400796286,
+      "grad_norm": 1.6380120481890832,
+      "learning_rate": 9.781831074633703e-06,
+      "loss": 1.2153,
+      "step": 151
+    },
+    {
+      "epoch": 0.40345056403450563,
+      "grad_norm": 1.9786402997029178,
+      "learning_rate": 9.778748613770234e-06,
+      "loss": 1.2213,
+      "step": 152
+    },
+    {
+      "epoch": 0.40610484406104846,
+      "grad_norm": 1.5864201917409944,
+      "learning_rate": 9.775645022270448e-06,
+      "loss": 1.1674,
+      "step": 153
+    },
+    {
+      "epoch": 0.40875912408759124,
+      "grad_norm": 1.6501859286504295,
+      "learning_rate": 9.772520313857777e-06,
+      "loss": 1.1805,
+      "step": 154
+    },
+    {
+      "epoch": 0.411413404114134,
+      "grad_norm": 1.5132303328319994,
+      "learning_rate": 9.769374502349038e-06,
+      "loss": 1.15,
+      "step": 155
+    },
+    {
+      "epoch": 0.41406768414067685,
+      "grad_norm": 1.6907615300646948,
+      "learning_rate": 9.766207601654356e-06,
+      "loss": 1.1848,
+      "step": 156
+    },
+    {
+      "epoch": 0.4167219641672196,
+      "grad_norm": 1.7001401085077357,
+      "learning_rate": 9.763019625777111e-06,
+      "loss": 1.2335,
+      "step": 157
+    },
+    {
+      "epoch": 0.41937624419376246,
+      "grad_norm": 1.7600942954439958,
+      "learning_rate": 9.759810588813872e-06,
+      "loss": 1.1743,
+      "step": 158
+    },
+    {
+      "epoch": 0.42203052422030524,
+      "grad_norm": 1.6515697771161784,
+      "learning_rate": 9.756580504954334e-06,
+      "loss": 1.2276,
+      "step": 159
+    },
+    {
+      "epoch": 0.42468480424684807,
+      "grad_norm": 1.6967375558942543,
+      "learning_rate": 9.753329388481261e-06,
+      "loss": 1.2082,
+      "step": 160
+    },
+    {
+      "epoch": 0.42733908427339085,
+      "grad_norm": 1.7152427713922846,
+      "learning_rate": 9.750057253770413e-06,
+      "loss": 1.1458,
+      "step": 161
+    },
+    {
+      "epoch": 0.4299933642999336,
+      "grad_norm": 1.625060781845651,
+      "learning_rate": 9.746764115290496e-06,
+      "loss": 1.2033,
+      "step": 162
+    },
+    {
+      "epoch": 0.43264764432647645,
+      "grad_norm": 1.7069397928194143,
+      "learning_rate": 9.743449987603082e-06,
+      "loss": 1.2342,
+      "step": 163
+    },
+    {
+      "epoch": 0.43530192435301923,
+      "grad_norm": 1.708629436384557,
+      "learning_rate": 9.740114885362562e-06,
+      "loss": 1.2442,
+      "step": 164
+    },
+    {
+      "epoch": 0.43795620437956206,
+      "grad_norm": 1.5857203714681123,
+      "learning_rate": 9.736758823316062e-06,
+      "loss": 1.2097,
+      "step": 165
+    },
+    {
+      "epoch": 0.44061048440610484,
+      "grad_norm": 1.657268677184339,
+      "learning_rate": 9.733381816303395e-06,
+      "loss": 1.1215,
+      "step": 166
+    },
+    {
+      "epoch": 0.4432647644326476,
+      "grad_norm": 1.4640436666626744,
+      "learning_rate": 9.729983879256988e-06,
+      "loss": 1.1646,
+      "step": 167
+    },
+    {
+      "epoch": 0.44591904445919045,
+      "grad_norm": 1.6268091054804499,
+      "learning_rate": 9.726565027201813e-06,
+      "loss": 1.2264,
+      "step": 168
+    },
+    {
+      "epoch": 0.4485733244857332,
+      "grad_norm": 1.5858930123997803,
+      "learning_rate": 9.723125275255325e-06,
+      "loss": 1.1661,
+      "step": 169
+    },
+    {
+      "epoch": 0.45122760451227606,
+      "grad_norm": 1.5759031230494174,
+      "learning_rate": 9.719664638627395e-06,
+      "loss": 1.1558,
+      "step": 170
+    },
+    {
+      "epoch": 0.45388188453881884,
+      "grad_norm": 1.7486351365651316,
+      "learning_rate": 9.716183132620242e-06,
+      "loss": 1.19,
+      "step": 171
+    },
+    {
+      "epoch": 0.45653616456536167,
+      "grad_norm": 1.7251231178841304,
+      "learning_rate": 9.712680772628365e-06,
+      "loss": 1.2261,
+      "step": 172
+    },
+    {
+      "epoch": 0.45919044459190445,
+      "grad_norm": 1.6118734678264717,
+      "learning_rate": 9.70915757413847e-06,
+      "loss": 1.2014,
+      "step": 173
+    },
+    {
+      "epoch": 0.4618447246184472,
+      "grad_norm": 1.5762577213086215,
+      "learning_rate": 9.705613552729416e-06,
+      "loss": 1.1487,
+      "step": 174
+    },
+    {
+      "epoch": 0.46449900464499005,
+      "grad_norm": 1.5672859542358526,
+      "learning_rate": 9.702048724072128e-06,
+      "loss": 1.1892,
+      "step": 175
+    },
+    {
+      "epoch": 0.46715328467153283,
+      "grad_norm": 1.616073022266597,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 1.1718,
+      "step": 176
+    },
+    {
+      "epoch": 0.46980756469807566,
+      "grad_norm": 1.605222482810264,
+      "learning_rate": 9.694856708156526e-06,
+      "loss": 1.1022,
+      "step": 177
+    },
+    {
+      "epoch": 0.47246184472461844,
+      "grad_norm": 1.483617625625729,
+      "learning_rate": 9.691229552699817e-06,
+      "loss": 1.1204,
+      "step": 178
+    },
+    {
+      "epoch": 0.4751161247511613,
+      "grad_norm": 1.6018473502205803,
+      "learning_rate": 9.68758165359794e-06,
+      "loss": 1.1816,
+      "step": 179
+    },
+    {
+      "epoch": 0.47777040477770405,
+      "grad_norm": 1.5779836150848479,
+      "learning_rate": 9.683913026981155e-06,
+      "loss": 1.1871,
+      "step": 180
+    },
+    {
+      "epoch": 0.4804246848042468,
+      "grad_norm": 1.6463102663610685,
+      "learning_rate": 9.680223689071364e-06,
+      "loss": 1.1139,
+      "step": 181
+    },
+    {
+      "epoch": 0.48307896483078966,
+      "grad_norm": 1.7091000919337074,
+      "learning_rate": 9.676513656182059e-06,
+      "loss": 1.1695,
+      "step": 182
+    },
+    {
+      "epoch": 0.48573324485733244,
+      "grad_norm": 1.633509337933534,
+      "learning_rate": 9.672782944718234e-06,
+      "loss": 1.1811,
+      "step": 183
+    },
+    {
+      "epoch": 0.48838752488387527,
+      "grad_norm": 1.5767561431519088,
+      "learning_rate": 9.669031571176322e-06,
+      "loss": 1.2062,
+      "step": 184
+    },
+    {
+      "epoch": 0.49104180491041804,
+      "grad_norm": 1.6306907003550404,
+      "learning_rate": 9.665259552144122e-06,
+      "loss": 1.1829,
+      "step": 185
+    },
+    {
+      "epoch": 0.4936960849369608,
+      "grad_norm": 1.517988528061533,
+      "learning_rate": 9.66146690430072e-06,
+      "loss": 1.2014,
+      "step": 186
+    },
+    {
+      "epoch": 0.49635036496350365,
+      "grad_norm": 1.598871387440831,
+      "learning_rate": 9.657653644416417e-06,
+      "loss": 1.1496,
+      "step": 187
+    },
+    {
+      "epoch": 0.49900464499004643,
+      "grad_norm": 2.400377785726973,
+      "learning_rate": 9.65381978935266e-06,
+      "loss": 1.1905,
+      "step": 188
+    },
+    {
+      "epoch": 0.5016589250165893,
+      "grad_norm": 1.5306038174802905,
+      "learning_rate": 9.649965356061961e-06,
+      "loss": 1.1225,
+      "step": 189
+    },
+    {
+      "epoch": 0.504313205043132,
+      "grad_norm": 1.7432637039460837,
+      "learning_rate": 9.646090361587828e-06,
+      "loss": 1.2338,
+      "step": 190
+    },
+    {
+      "epoch": 0.5069674850696748,
+      "grad_norm": 1.549174772320108,
+      "learning_rate": 9.642194823064679e-06,
+      "loss": 1.1395,
+      "step": 191
+    },
+    {
+      "epoch": 0.5096217650962177,
+      "grad_norm": 1.4556718082039433,
+      "learning_rate": 9.63827875771778e-06,
+      "loss": 1.1054,
+      "step": 192
+    },
+    {
+      "epoch": 0.5122760451227605,
+      "grad_norm": 1.546232476076245,
+      "learning_rate": 9.634342182863163e-06,
+      "loss": 1.1821,
+      "step": 193
+    },
+    {
+      "epoch": 0.5149303251493033,
+      "grad_norm": 1.6428065540768686,
+      "learning_rate": 9.630385115907545e-06,
+      "loss": 1.2078,
+      "step": 194
+    },
+    {
+      "epoch": 0.517584605175846,
+      "grad_norm": 1.5932949193165389,
+      "learning_rate": 9.626407574348258e-06,
+      "loss": 1.1646,
+      "step": 195
+    },
+    {
+      "epoch": 0.5202388852023888,
+      "grad_norm": 1.5803201555935116,
+      "learning_rate": 9.622409575773162e-06,
+      "loss": 1.166,
+      "step": 196
+    },
+    {
+      "epoch": 0.5228931652289317,
+      "grad_norm": 1.5292820314306055,
+      "learning_rate": 9.618391137860583e-06,
+      "loss": 1.2152,
+      "step": 197
+    },
+    {
+      "epoch": 0.5255474452554745,
+      "grad_norm": 1.3727930028186761,
+      "learning_rate": 9.614352278379217e-06,
+      "loss": 1.1402,
+      "step": 198
+    },
+    {
+      "epoch": 0.5282017252820173,
+      "grad_norm": 1.6819090165661312,
+      "learning_rate": 9.610293015188067e-06,
+      "loss": 1.1665,
+      "step": 199
+    },
+    {
+      "epoch": 0.53085600530856,
+      "grad_norm": 1.5006037012098021,
+      "learning_rate": 9.606213366236354e-06,
+      "loss": 1.1877,
+      "step": 200
+    },
+    {
+      "epoch": 0.5335102853351028,
+      "grad_norm": 1.6016624668408799,
+      "learning_rate": 9.60211334956344e-06,
+      "loss": 1.1498,
+      "step": 201
+    },
+    {
+      "epoch": 0.5361645653616457,
+      "grad_norm": 1.7368140744461305,
+      "learning_rate": 9.597992983298748e-06,
+      "loss": 1.1922,
+      "step": 202
+    },
+    {
+      "epoch": 0.5388188453881885,
+      "grad_norm": 1.6176251602621352,
+      "learning_rate": 9.593852285661684e-06,
+      "loss": 1.1459,
+      "step": 203
+    },
+    {
+      "epoch": 0.5414731254147312,
+      "grad_norm": 1.3750495471617235,
+      "learning_rate": 9.589691274961556e-06,
+      "loss": 1.0835,
+      "step": 204
+    },
+    {
+      "epoch": 0.544127405441274,
+      "grad_norm": 1.6906485599869903,
+      "learning_rate": 9.585509969597491e-06,
+      "loss": 1.22,
+      "step": 205
+    },
+    {
+      "epoch": 0.5467816854678168,
+      "grad_norm": 1.5439326128894457,
+      "learning_rate": 9.581308388058354e-06,
+      "loss": 1.1364,
+      "step": 206
+    },
+    {
+      "epoch": 0.5494359654943597,
+      "grad_norm": 1.5251041120197495,
+      "learning_rate": 9.577086548922671e-06,
+      "loss": 1.2201,
+      "step": 207
+    },
+    {
+      "epoch": 0.5520902455209025,
+      "grad_norm": 1.511712369802414,
+      "learning_rate": 9.572844470858537e-06,
+      "loss": 1.1091,
+      "step": 208
+    },
+    {
+      "epoch": 0.5547445255474452,
+      "grad_norm": 1.8573483808679467,
+      "learning_rate": 9.568582172623544e-06,
+      "loss": 1.2284,
+      "step": 209
+    },
+    {
+      "epoch": 0.557398805573988,
+      "grad_norm": 1.4309251806187955,
+      "learning_rate": 9.56429967306469e-06,
+      "loss": 1.1646,
+      "step": 210
+    },
+    {
+      "epoch": 0.5600530856005309,
+      "grad_norm": 1.6268260856080405,
+      "learning_rate": 9.559996991118304e-06,
+      "loss": 1.1812,
+      "step": 211
+    },
+    {
+      "epoch": 0.5627073656270737,
+      "grad_norm": 1.6752285964398912,
+      "learning_rate": 9.55567414580995e-06,
+      "loss": 1.19,
+      "step": 212
+    },
+    {
+      "epoch": 0.5653616456536165,
+      "grad_norm": 1.6202125494829664,
+      "learning_rate": 9.551331156254358e-06,
+      "loss": 1.2001,
+      "step": 213
+    },
+    {
+      "epoch": 0.5680159256801592,
+      "grad_norm": 1.4441208249265054,
+      "learning_rate": 9.546968041655326e-06,
+      "loss": 1.2011,
+      "step": 214
+    },
+    {
+      "epoch": 0.570670205706702,
+      "grad_norm": 1.4681168393734876,
+      "learning_rate": 9.542584821305643e-06,
+      "loss": 1.118,
+      "step": 215
+    },
+    {
+      "epoch": 0.5733244857332449,
+      "grad_norm": 1.67215223118757,
+      "learning_rate": 9.538181514587004e-06,
+      "loss": 1.1441,
+      "step": 216
+    },
+    {
+      "epoch": 0.5759787657597877,
+      "grad_norm": 1.840004210878956,
+      "learning_rate": 9.533758140969913e-06,
+      "loss": 1.1689,
+      "step": 217
+    },
+    {
+      "epoch": 0.5786330457863305,
+      "grad_norm": 2.0817799067244387,
+      "learning_rate": 9.529314720013618e-06,
+      "loss": 1.1879,
+      "step": 218
+    },
+    {
+      "epoch": 0.5812873258128732,
+      "grad_norm": 1.6384013753881452,
+      "learning_rate": 9.524851271366002e-06,
+      "loss": 1.1157,
+      "step": 219
+    },
+    {
+      "epoch": 0.583941605839416,
+      "grad_norm": 1.6847540459176993,
+      "learning_rate": 9.520367814763514e-06,
+      "loss": 1.1583,
+      "step": 220
+    },
+    {
+      "epoch": 0.5865958858659589,
+      "grad_norm": 1.553367758905212,
+      "learning_rate": 9.515864370031066e-06,
+      "loss": 1.0916,
+      "step": 221
+    },
+    {
+      "epoch": 0.5892501658925017,
+      "grad_norm": 1.6595661898312408,
+      "learning_rate": 9.511340957081957e-06,
+      "loss": 1.1912,
+      "step": 222
+    },
+    {
+      "epoch": 0.5919044459190445,
+      "grad_norm": 1.6816767854984012,
+      "learning_rate": 9.506797595917787e-06,
+      "loss": 1.1948,
+      "step": 223
+    },
+    {
+      "epoch": 0.5945587259455872,
+      "grad_norm": 1.4766094174812612,
+      "learning_rate": 9.502234306628354e-06,
+      "loss": 1.1607,
+      "step": 224
+    },
+    {
+      "epoch": 0.59721300597213,
+      "grad_norm": 1.5815513019760774,
+      "learning_rate": 9.49765110939158e-06,
+      "loss": 1.1248,
+      "step": 225
+    },
+    {
+      "epoch": 0.5998672859986729,
+      "grad_norm": 1.6485658910927394,
+      "learning_rate": 9.493048024473413e-06,
+      "loss": 1.2191,
+      "step": 226
+    },
+    {
+      "epoch": 0.6025215660252157,
+      "grad_norm": 1.424065848656427,
+      "learning_rate": 9.488425072227738e-06,
+      "loss": 1.2521,
+      "step": 227
+    },
+    {
+      "epoch": 0.6051758460517584,
+      "grad_norm": 1.4486333802405926,
+      "learning_rate": 9.483782273096295e-06,
+      "loss": 1.1734,
+      "step": 228
+    },
+    {
+      "epoch": 0.6078301260783012,
+      "grad_norm": 1.6817918601770532,
+      "learning_rate": 9.47911964760858e-06,
+      "loss": 1.1695,
+      "step": 229
+    },
+    {
+      "epoch": 0.6104844061048441,
+      "grad_norm": 1.6160290558732326,
+      "learning_rate": 9.474437216381756e-06,
+      "loss": 1.154,
+      "step": 230
+    },
+    {
+      "epoch": 0.6131386861313869,
+      "grad_norm": 1.4261795572898603,
+      "learning_rate": 9.469735000120564e-06,
+      "loss": 1.1544,
+      "step": 231
+    },
+    {
+      "epoch": 0.6157929661579297,
+      "grad_norm": 1.458151411666846,
+      "learning_rate": 9.46501301961723e-06,
+      "loss": 1.2065,
+      "step": 232
+    },
+    {
+      "epoch": 0.6184472461844724,
+      "grad_norm": 1.5627499060274408,
+      "learning_rate": 9.460271295751373e-06,
+      "loss": 1.1579,
+      "step": 233
+    },
+    {
+      "epoch": 0.6211015262110152,
+      "grad_norm": 1.86944032236805,
+      "learning_rate": 9.455509849489915e-06,
+      "loss": 1.1519,
+      "step": 234
+    },
+    {
+      "epoch": 0.6237558062375581,
+      "grad_norm": 1.979766174904363,
+      "learning_rate": 9.450728701886985e-06,
+      "loss": 1.2358,
+      "step": 235
+    },
+    {
+      "epoch": 0.6264100862641009,
+      "grad_norm": 1.5229843416844162,
+      "learning_rate": 9.445927874083825e-06,
+      "loss": 1.1207,
+      "step": 236
+    },
+    {
+      "epoch": 0.6290643662906437,
+      "grad_norm": 1.5916340950774943,
+      "learning_rate": 9.441107387308701e-06,
+      "loss": 1.2486,
+      "step": 237
+    },
+    {
+      "epoch": 0.6317186463171864,
+      "grad_norm": 1.4982052500691954,
+      "learning_rate": 9.436267262876808e-06,
+      "loss": 1.1445,
+      "step": 238
+    },
+    {
+      "epoch": 0.6343729263437292,
+      "grad_norm": 1.868028818978397,
+      "learning_rate": 9.431407522190176e-06,
+      "loss": 1.2215,
+      "step": 239
+    },
+    {
+      "epoch": 0.6370272063702721,
+      "grad_norm": 1.5000893386206633,
+      "learning_rate": 9.426528186737566e-06,
+      "loss": 1.1748,
+      "step": 240
+    },
+    {
+      "epoch": 0.6396814863968149,
+      "grad_norm": 1.6105517075622542,
+      "learning_rate": 9.421629278094394e-06,
+      "loss": 1.1444,
+      "step": 241
+    },
+    {
+      "epoch": 0.6423357664233577,
+      "grad_norm": 1.6245044582496362,
+      "learning_rate": 9.416710817922615e-06,
+      "loss": 1.2016,
+      "step": 242
+    },
+    {
+      "epoch": 0.6449900464499004,
+      "grad_norm": 1.582791773770731,
+      "learning_rate": 9.411772827970642e-06,
+      "loss": 1.1595,
+      "step": 243
+    },
+    {
+      "epoch": 0.6476443264764432,
+      "grad_norm": 1.5289298221123744,
+      "learning_rate": 9.406815330073244e-06,
+      "loss": 1.196,
+      "step": 244
+    },
+    {
+      "epoch": 0.6502986065029861,
+      "grad_norm": 1.494805179412693,
+      "learning_rate": 9.40183834615145e-06,
+      "loss": 1.119,
+      "step": 245
+    },
+    {
+      "epoch": 0.6529528865295289,
+      "grad_norm": 1.6857955705395817,
+      "learning_rate": 9.396841898212452e-06,
+      "loss": 1.1222,
+      "step": 246
+    },
+    {
+      "epoch": 0.6556071665560717,
+      "grad_norm": 1.465569644664737,
+      "learning_rate": 9.391826008349507e-06,
+      "loss": 1.1196,
+      "step": 247
+    },
+    {
+      "epoch": 0.6582614465826144,
+      "grad_norm": 1.6038700287536702,
+      "learning_rate": 9.38679069874184e-06,
+      "loss": 1.1596,
+      "step": 248
+    },
+    {
+      "epoch": 0.6609157266091573,
+      "grad_norm": 1.754259412074635,
+      "learning_rate": 9.381735991654547e-06,
+      "loss": 1.185,
+      "step": 249
+    },
+    {
+      "epoch": 0.6635700066357001,
+      "grad_norm": 1.5054976516017162,
+      "learning_rate": 9.376661909438496e-06,
+      "loss": 1.14,
+      "step": 250
+    },
+    {
+      "epoch": 0.6662242866622429,
+      "grad_norm": 1.6591136646331954,
+      "learning_rate": 9.371568474530228e-06,
+      "loss": 1.1453,
+      "step": 251
+    },
+    {
+      "epoch": 0.6688785666887856,
+      "grad_norm": 1.602614315373211,
+      "learning_rate": 9.366455709451857e-06,
+      "loss": 1.115,
+      "step": 252
+    },
+    {
+      "epoch": 0.6715328467153284,
+      "grad_norm": 1.3802344389470933,
+      "learning_rate": 9.36132363681097e-06,
+      "loss": 1.0926,
+      "step": 253
+    },
+    {
+      "epoch": 0.6741871267418713,
+      "grad_norm": 1.5028041314507699,
+      "learning_rate": 9.356172279300528e-06,
+      "loss": 1.1388,
+      "step": 254
+    },
+    {
+      "epoch": 0.6768414067684141,
+      "grad_norm": 1.4603385973006835,
+      "learning_rate": 9.35100165969877e-06,
+      "loss": 1.1261,
+      "step": 255
+    },
+    {
+      "epoch": 0.6794956867949569,
+      "grad_norm": 2.222737357031752,
+      "learning_rate": 9.3458118008691e-06,
+      "loss": 1.1181,
+      "step": 256
+    },
+    {
+      "epoch": 0.6821499668214996,
+      "grad_norm": 1.5628150576174966,
+      "learning_rate": 9.340602725760003e-06,
+      "loss": 1.1269,
+      "step": 257
+    },
+    {
+      "epoch": 0.6848042468480424,
+      "grad_norm": 1.7660936315398623,
+      "learning_rate": 9.335374457404928e-06,
+      "loss": 1.1567,
+      "step": 258
+    },
+    {
+      "epoch": 0.6874585268745853,
+      "grad_norm": 1.5095573241471834,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 1.1407,
+      "step": 259
+    },
+    {
+      "epoch": 0.6901128069011281,
+      "grad_norm": 1.4506359372228914,
+      "learning_rate": 9.324860433514888e-06,
+      "loss": 1.1668,
+      "step": 260
+    },
+    {
+      "epoch": 0.6927670869276709,
+      "grad_norm": 1.536882345986633,
+      "learning_rate": 9.319574724470756e-06,
+      "loss": 1.1581,
+      "step": 261
+    },
+    {
+      "epoch": 0.6954213669542136,
+      "grad_norm": 1.4356269422691534,
+      "learning_rate": 9.314269915162115e-06,
+      "loss": 1.1075,
+      "step": 262
+    },
+    {
+      "epoch": 0.6980756469807564,
+      "grad_norm": 1.373904876593965,
+      "learning_rate": 9.308946029045726e-06,
+      "loss": 1.1121,
+      "step": 263
+    },
+    {
+      "epoch": 0.7007299270072993,
+      "grad_norm": 1.5328812905843867,
+      "learning_rate": 9.303603089662717e-06,
+      "loss": 1.0921,
+      "step": 264
+    },
+    {
+      "epoch": 0.7033842070338421,
+      "grad_norm": 1.5072781837506157,
+      "learning_rate": 9.298241120638451e-06,
+      "loss": 1.1198,
+      "step": 265
+    },
+    {
+      "epoch": 0.7060384870603849,
+      "grad_norm": 1.5995295442728128,
+      "learning_rate": 9.292860145682451e-06,
+      "loss": 1.1472,
+      "step": 266
+    },
+    {
+      "epoch": 0.7086927670869276,
+      "grad_norm": 1.586589487215959,
+      "learning_rate": 9.287460188588272e-06,
+      "loss": 1.2081,
+      "step": 267
+    },
+    {
+      "epoch": 0.7113470471134705,
+      "grad_norm": 1.6738675413951511,
+      "learning_rate": 9.282041273233402e-06,
+      "loss": 1.1676,
+      "step": 268
+    },
+    {
+      "epoch": 0.7140013271400133,
+      "grad_norm": 1.5986869946296454,
+      "learning_rate": 9.276603423579164e-06,
+      "loss": 1.213,
+      "step": 269
+    },
+    {
+      "epoch": 0.7166556071665561,
+      "grad_norm": 1.5027119454217344,
+      "learning_rate": 9.271146663670605e-06,
+      "loss": 1.1622,
+      "step": 270
+    },
+    {
+      "epoch": 0.7193098871930989,
+      "grad_norm": 1.4752249291840163,
+      "learning_rate": 9.265671017636384e-06,
+      "loss": 1.0725,
+      "step": 271
+    },
+    {
+      "epoch": 0.7219641672196416,
+      "grad_norm": 1.6425492982199013,
+      "learning_rate": 9.260176509688673e-06,
+      "loss": 1.2088,
+      "step": 272
+    },
+    {
+      "epoch": 0.7246184472461845,
+      "grad_norm": 1.671119694405482,
+      "learning_rate": 9.254663164123052e-06,
+      "loss": 1.1584,
+      "step": 273
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 3.2839083971639016,
+      "learning_rate": 9.249131005318388e-06,
+      "loss": 1.0801,
+      "step": 274
+    },
+    {
+      "epoch": 0.7299270072992701,
+      "grad_norm": 1.590670276122513,
+      "learning_rate": 9.243580057736743e-06,
+      "loss": 1.1157,
+      "step": 275
+    },
+    {
+      "epoch": 0.7325812873258128,
+      "grad_norm": 1.4517652800533363,
+      "learning_rate": 9.238010345923257e-06,
+      "loss": 1.1446,
+      "step": 276
+    },
+    {
+      "epoch": 0.7352355673523556,
+      "grad_norm": 1.9696673043614277,
+      "learning_rate": 9.232421894506043e-06,
+      "loss": 1.1857,
+      "step": 277
+    },
+    {
+      "epoch": 0.7378898473788985,
+      "grad_norm": 1.4778960277561557,
+      "learning_rate": 9.226814728196072e-06,
+      "loss": 1.1397,
+      "step": 278
+    },
+    {
+      "epoch": 0.7405441274054413,
+      "grad_norm": 1.6498804570471097,
+      "learning_rate": 9.221188871787076e-06,
+      "loss": 1.1625,
+      "step": 279
+    },
+    {
+      "epoch": 0.7431984074319841,
+      "grad_norm": 1.5796993896804141,
+      "learning_rate": 9.215544350155423e-06,
+      "loss": 1.1459,
+      "step": 280
+    },
+    {
+      "epoch": 0.7458526874585268,
+      "grad_norm": 1.5226644568838132,
+      "learning_rate": 9.209881188260021e-06,
+      "loss": 1.1894,
+      "step": 281
+    },
+    {
+      "epoch": 0.7485069674850697,
+      "grad_norm": 1.6645552718061039,
+      "learning_rate": 9.204199411142196e-06,
+      "loss": 1.0811,
+      "step": 282
+    },
+    {
+      "epoch": 0.7511612475116125,
+      "grad_norm": 1.6581847965929961,
+      "learning_rate": 9.198499043925591e-06,
+      "loss": 1.1706,
+      "step": 283
+    },
+    {
+      "epoch": 0.7538155275381553,
+      "grad_norm": 1.5270964606037345,
+      "learning_rate": 9.192780111816048e-06,
+      "loss": 1.1009,
+      "step": 284
+    },
+    {
+      "epoch": 0.7564698075646981,
+      "grad_norm": 1.6698962782227256,
+      "learning_rate": 9.1870426401015e-06,
+      "loss": 1.1708,
+      "step": 285
+    },
+    {
+      "epoch": 0.7591240875912408,
+      "grad_norm": 1.7012646465038568,
+      "learning_rate": 9.18128665415186e-06,
+      "loss": 1.1728,
+      "step": 286
+    },
+    {
+      "epoch": 0.7617783676177837,
+      "grad_norm": 1.4354980241800914,
+      "learning_rate": 9.175512179418903e-06,
+      "loss": 1.1138,
+      "step": 287
+    },
+    {
+      "epoch": 0.7644326476443265,
+      "grad_norm": 1.5648924104277102,
+      "learning_rate": 9.169719241436162e-06,
+      "loss": 1.0936,
+      "step": 288
+    },
+    {
+      "epoch": 0.7670869276708693,
+      "grad_norm": 1.535950564272176,
+      "learning_rate": 9.163907865818806e-06,
+      "loss": 1.0884,
+      "step": 289
+    },
+    {
+      "epoch": 0.769741207697412,
+      "grad_norm": 1.4657493870841045,
+      "learning_rate": 9.158078078263536e-06,
+      "loss": 1.0962,
+      "step": 290
+    },
+    {
+      "epoch": 0.7723954877239548,
+      "grad_norm": 1.5960566218254721,
+      "learning_rate": 9.152229904548464e-06,
+      "loss": 1.1003,
+      "step": 291
+    },
+    {
+      "epoch": 0.7750497677504977,
+      "grad_norm": 1.5026317273526155,
+      "learning_rate": 9.146363370533004e-06,
+      "loss": 1.1334,
+      "step": 292
+    },
+    {
+      "epoch": 0.7777040477770405,
+      "grad_norm": 1.4667451034506551,
+      "learning_rate": 9.14047850215775e-06,
+      "loss": 1.188,
+      "step": 293
+    },
+    {
+      "epoch": 0.7803583278035833,
+      "grad_norm": 2.5527846830656773,
+      "learning_rate": 9.134575325444377e-06,
+      "loss": 1.1489,
+      "step": 294
+    },
+    {
+      "epoch": 0.783012607830126,
+      "grad_norm": 1.5656317760690617,
+      "learning_rate": 9.128653866495504e-06,
+      "loss": 1.1049,
+      "step": 295
+    },
+    {
+      "epoch": 0.7856668878566688,
+      "grad_norm": 1.4532042000319447,
+      "learning_rate": 9.122714151494599e-06,
+      "loss": 1.1156,
+      "step": 296
+    },
+    {
+      "epoch": 0.7883211678832117,
+      "grad_norm": 1.4759483242959985,
+      "learning_rate": 9.116756206705848e-06,
+      "loss": 1.1396,
+      "step": 297
+    },
+    {
+      "epoch": 0.7909754479097545,
+      "grad_norm": 1.4531099151254951,
+      "learning_rate": 9.110780058474052e-06,
+      "loss": 1.1011,
+      "step": 298
+    },
+    {
+      "epoch": 0.7936297279362973,
+      "grad_norm": 1.509245001105786,
+      "learning_rate": 9.104785733224498e-06,
+      "loss": 1.1052,
+      "step": 299
+    },
+    {
+      "epoch": 0.79628400796284,
+      "grad_norm": 1.4742686115404562,
+      "learning_rate": 9.09877325746285e-06,
+      "loss": 1.1627,
+      "step": 300
+    },
+    {
+      "epoch": 0.7989382879893829,
+      "grad_norm": 1.4451227706627736,
+      "learning_rate": 9.092742657775031e-06,
+      "loss": 1.1118,
+      "step": 301
+    },
+    {
+      "epoch": 0.8015925680159257,
+      "grad_norm": 1.575230566769605,
+      "learning_rate": 9.086693960827106e-06,
+      "loss": 1.1625,
+      "step": 302
+    },
+    {
+      "epoch": 0.8042468480424685,
+      "grad_norm": 1.6679637319120473,
+      "learning_rate": 9.080627193365155e-06,
+      "loss": 1.1452,
+      "step": 303
+    },
+    {
+      "epoch": 0.8069011280690113,
+      "grad_norm": 1.4072750238146392,
+      "learning_rate": 9.07454238221517e-06,
+      "loss": 1.1121,
+      "step": 304
+    },
+    {
+      "epoch": 0.809555408095554,
+      "grad_norm": 1.399645387242144,
+      "learning_rate": 9.068439554282924e-06,
+      "loss": 1.1101,
+      "step": 305
+    },
+    {
+      "epoch": 0.8122096881220969,
+      "grad_norm": 1.9740369624876526,
+      "learning_rate": 9.06231873655386e-06,
+      "loss": 1.0986,
+      "step": 306
+    },
+    {
+      "epoch": 0.8148639681486397,
+      "grad_norm": 1.4581046261229995,
+      "learning_rate": 9.056179956092961e-06,
+      "loss": 1.1228,
+      "step": 307
+    },
+    {
+      "epoch": 0.8175182481751825,
+      "grad_norm": 2.628430909687979,
+      "learning_rate": 9.050023240044649e-06,
+      "loss": 1.0783,
+      "step": 308
+    },
+    {
+      "epoch": 0.8201725282017253,
+      "grad_norm": 1.6691124773863195,
+      "learning_rate": 9.043848615632643e-06,
+      "loss": 1.167,
+      "step": 309
+    },
+    {
+      "epoch": 0.822826808228268,
+      "grad_norm": 1.7459906965590473,
+      "learning_rate": 9.03765611015985e-06,
+      "loss": 1.2287,
+      "step": 310
+    },
+    {
+      "epoch": 0.8254810882548109,
+      "grad_norm": 1.5373249007323673,
+      "learning_rate": 9.031445751008252e-06,
+      "loss": 1.1446,
+      "step": 311
+    },
+    {
+      "epoch": 0.8281353682813537,
+      "grad_norm": 1.526522854497616,
+      "learning_rate": 9.025217565638766e-06,
+      "loss": 1.1609,
+      "step": 312
+    },
+    {
+      "epoch": 0.8307896483078965,
+      "grad_norm": 1.3715974716678416,
+      "learning_rate": 9.018971581591141e-06,
+      "loss": 1.1761,
+      "step": 313
+    },
+    {
+      "epoch": 0.8334439283344393,
+      "grad_norm": 1.733161587991312,
+      "learning_rate": 9.012707826483823e-06,
+      "loss": 1.1241,
+      "step": 314
+    },
+    {
+      "epoch": 0.836098208360982,
+      "grad_norm": 1.5851407690090333,
+      "learning_rate": 9.006426328013838e-06,
+      "loss": 1.1898,
+      "step": 315
+    },
+    {
+      "epoch": 0.8387524883875249,
+      "grad_norm": 1.492565448115301,
+      "learning_rate": 9.000127113956673e-06,
+      "loss": 1.1281,
+      "step": 316
+    },
+    {
+      "epoch": 0.8414067684140677,
+      "grad_norm": 1.4675427619453145,
+      "learning_rate": 8.993810212166147e-06,
+      "loss": 1.1078,
+      "step": 317
+    },
+    {
+      "epoch": 0.8440610484406105,
+      "grad_norm": 1.7806802137808329,
+      "learning_rate": 8.987475650574289e-06,
+      "loss": 1.1113,
+      "step": 318
+    },
+    {
+      "epoch": 0.8467153284671532,
+      "grad_norm": 1.7957085592461643,
+      "learning_rate": 8.98112345719122e-06,
+      "loss": 1.0371,
+      "step": 319
+    },
+    {
+      "epoch": 0.8493696084936961,
+      "grad_norm": 1.6891739001445774,
+      "learning_rate": 8.974753660105023e-06,
+      "loss": 1.1939,
+      "step": 320
+    },
+    {
+      "epoch": 0.8520238885202389,
+      "grad_norm": 1.361414937851007,
+      "learning_rate": 8.968366287481621e-06,
+      "loss": 1.0606,
+      "step": 321
+    },
+    {
+      "epoch": 0.8546781685467817,
+      "grad_norm": 1.5477011631255944,
+      "learning_rate": 8.961961367564652e-06,
+      "loss": 1.1343,
+      "step": 322
+    },
+    {
+      "epoch": 0.8573324485733245,
+      "grad_norm": 1.398038196798421,
+      "learning_rate": 8.955538928675343e-06,
+      "loss": 1.0537,
+      "step": 323
+    },
+    {
+      "epoch": 0.8599867285998672,
+      "grad_norm": 1.4829616588106211,
+      "learning_rate": 8.94909899921239e-06,
+      "loss": 1.1244,
+      "step": 324
+    },
+    {
+      "epoch": 0.8626410086264101,
+      "grad_norm": 1.458234865181319,
+      "learning_rate": 8.94264160765183e-06,
+      "loss": 1.0945,
+      "step": 325
+    },
+    {
+      "epoch": 0.8652952886529529,
+      "grad_norm": 1.48674147774638,
+      "learning_rate": 8.936166782546907e-06,
+      "loss": 1.0698,
+      "step": 326
+    },
+    {
+      "epoch": 0.8679495686794957,
+      "grad_norm": 1.3468414140104497,
+      "learning_rate": 8.929674552527956e-06,
+      "loss": 1.0428,
+      "step": 327
+    },
+    {
+      "epoch": 0.8706038487060385,
+      "grad_norm": 1.4927690225590464,
+      "learning_rate": 8.923164946302274e-06,
+      "loss": 1.1367,
+      "step": 328
+    },
+    {
+      "epoch": 0.8732581287325812,
+      "grad_norm": 1.3780023302624582,
+      "learning_rate": 8.91663799265399e-06,
+      "loss": 1.1048,
+      "step": 329
+    },
+    {
+      "epoch": 0.8759124087591241,
+      "grad_norm": 1.8364949062401694,
+      "learning_rate": 8.910093720443945e-06,
+      "loss": 1.1962,
+      "step": 330
+    },
+    {
+      "epoch": 0.8785666887856669,
+      "grad_norm": 1.6803377587803117,
+      "learning_rate": 8.903532158609548e-06,
+      "loss": 1.1919,
+      "step": 331
+    },
+    {
+      "epoch": 0.8812209688122097,
+      "grad_norm": 1.5621810302199315,
+      "learning_rate": 8.89695333616467e-06,
+      "loss": 1.1177,
+      "step": 332
+    },
+    {
+      "epoch": 0.8838752488387525,
+      "grad_norm": 1.4462262022449852,
+      "learning_rate": 8.890357282199504e-06,
+      "loss": 1.1321,
+      "step": 333
+    },
+    {
+      "epoch": 0.8865295288652952,
+      "grad_norm": 1.4286236136174415,
+      "learning_rate": 8.883744025880429e-06,
+      "loss": 1.1717,
+      "step": 334
+    },
+    {
+      "epoch": 0.8891838088918381,
+      "grad_norm": 1.4484748876813012,
+      "learning_rate": 8.877113596449895e-06,
+      "loss": 1.1004,
+      "step": 335
+    },
+    {
+      "epoch": 0.8918380889183809,
+      "grad_norm": 1.4164984401949983,
+      "learning_rate": 8.87046602322629e-06,
+      "loss": 1.079,
+      "step": 336
+    },
+    {
+      "epoch": 0.8944923689449237,
+      "grad_norm": 1.3708607011124272,
+      "learning_rate": 8.863801335603802e-06,
+      "loss": 1.133,
+      "step": 337
+    },
+    {
+      "epoch": 0.8971466489714665,
+      "grad_norm": 1.3626382714893748,
+      "learning_rate": 8.857119563052301e-06,
+      "loss": 1.0734,
+      "step": 338
+    },
+    {
+      "epoch": 0.8998009289980093,
+      "grad_norm": 1.5082034601534042,
+      "learning_rate": 8.850420735117202e-06,
+      "loss": 1.1691,
+      "step": 339
+    },
+    {
+      "epoch": 0.9024552090245521,
+      "grad_norm": 1.3234730893075355,
+      "learning_rate": 8.843704881419333e-06,
+      "loss": 1.046,
+      "step": 340
+    },
+    {
+      "epoch": 0.9051094890510949,
+      "grad_norm": 1.4896833219647911,
+      "learning_rate": 8.836972031654807e-06,
+      "loss": 1.1586,
+      "step": 341
+    },
+    {
+      "epoch": 0.9077637690776377,
+      "grad_norm": 1.3697029850159739,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 1.0817,
+      "step": 342
+    },
+    {
+      "epoch": 0.9104180491041804,
+      "grad_norm": 1.747564979115208,
+      "learning_rate": 8.823455463085873e-06,
+      "loss": 1.0905,
+      "step": 343
+    },
+    {
+      "epoch": 0.9130723291307233,
+      "grad_norm": 1.5649272934153584,
+      "learning_rate": 8.816671804048933e-06,
+      "loss": 1.0434,
+      "step": 344
+    },
+    {
+      "epoch": 0.9157266091572661,
+      "grad_norm": 1.4823250348157,
+      "learning_rate": 8.809871268480004e-06,
+      "loss": 1.0895,
+      "step": 345
+    },
+    {
+      "epoch": 0.9183808891838089,
+      "grad_norm": 1.4264959835661182,
+      "learning_rate": 8.803053886449644e-06,
+      "loss": 1.1502,
+      "step": 346
+    },
+    {
+      "epoch": 0.9210351692103517,
+      "grad_norm": 1.5424239648407791,
+      "learning_rate": 8.796219688102906e-06,
+      "loss": 1.0734,
+      "step": 347
+    },
+    {
+      "epoch": 0.9236894492368944,
+      "grad_norm": 1.594778792432936,
+      "learning_rate": 8.789368703659199e-06,
+      "loss": 1.06,
+      "step": 348
+    },
+    {
+      "epoch": 0.9263437292634373,
+      "grad_norm": 1.425756455063989,
+      "learning_rate": 8.782500963412156e-06,
+      "loss": 1.1091,
+      "step": 349
+    },
+    {
+      "epoch": 0.9289980092899801,
+      "grad_norm": 1.4480941030784251,
+      "learning_rate": 8.775616497729502e-06,
+      "loss": 1.1146,
+      "step": 350
+    },
+    {
+      "epoch": 0.9316522893165229,
+      "grad_norm": 1.9595578470904635,
+      "learning_rate": 8.768715337052918e-06,
+      "loss": 1.1353,
+      "step": 351
+    },
+    {
+      "epoch": 0.9343065693430657,
+      "grad_norm": 1.6462295827570508,
+      "learning_rate": 8.761797511897907e-06,
+      "loss": 1.1376,
+      "step": 352
+    },
+    {
+      "epoch": 0.9369608493696084,
+      "grad_norm": 1.393588576405631,
+      "learning_rate": 8.754863052853658e-06,
+      "loss": 1.1317,
+      "step": 353
+    },
+    {
+      "epoch": 0.9396151293961513,
+      "grad_norm": 2.230474529090937,
+      "learning_rate": 8.747911990582912e-06,
+      "loss": 1.1086,
+      "step": 354
+    },
+    {
+      "epoch": 0.9422694094226941,
+      "grad_norm": 1.809443765521074,
+      "learning_rate": 8.740944355821827e-06,
+      "loss": 1.1018,
+      "step": 355
+    },
+    {
+      "epoch": 0.9449236894492369,
+      "grad_norm": 1.6826959358419462,
+      "learning_rate": 8.733960179379842e-06,
+      "loss": 1.1766,
+      "step": 356
+    },
+    {
+      "epoch": 0.9475779694757797,
+      "grad_norm": 1.429793323082417,
+      "learning_rate": 8.726959492139535e-06,
+      "loss": 1.062,
+      "step": 357
+    },
+    {
+      "epoch": 0.9502322495023225,
+      "grad_norm": 1.3304241051942485,
+      "learning_rate": 8.719942325056496e-06,
+      "loss": 1.0864,
+      "step": 358
+    },
+    {
+      "epoch": 0.9528865295288653,
+      "grad_norm": 1.838527760485716,
+      "learning_rate": 8.712908709159183e-06,
+      "loss": 1.08,
+      "step": 359
+    },
+    {
+      "epoch": 0.9555408095554081,
+      "grad_norm": 1.8095644142003555,
+      "learning_rate": 8.70585867554879e-06,
+      "loss": 1.0622,
+      "step": 360
+    },
+    {
+      "epoch": 0.9581950895819509,
+      "grad_norm": 1.3961944428914481,
+      "learning_rate": 8.698792255399104e-06,
+      "loss": 1.1279,
+      "step": 361
+    },
+    {
+      "epoch": 0.9608493696084937,
+      "grad_norm": 1.4265196608054989,
+      "learning_rate": 8.691709479956373e-06,
+      "loss": 1.0786,
+      "step": 362
+    },
+    {
+      "epoch": 0.9635036496350365,
+      "grad_norm": 1.5175948559199692,
+      "learning_rate": 8.68461038053916e-06,
+      "loss": 1.1046,
+      "step": 363
+    },
+    {
+      "epoch": 0.9661579296615793,
+      "grad_norm": 1.5709878342434411,
+      "learning_rate": 8.67749498853821e-06,
+      "loss": 1.0947,
+      "step": 364
+    },
+    {
+      "epoch": 0.9688122096881221,
+      "grad_norm": 1.5372734019009258,
+      "learning_rate": 8.670363335416319e-06,
+      "loss": 1.0346,
+      "step": 365
+    },
+    {
+      "epoch": 0.9714664897146649,
+      "grad_norm": 1.3550031766754063,
+      "learning_rate": 8.663215452708173e-06,
+      "loss": 1.0868,
+      "step": 366
+    },
+    {
+      "epoch": 0.9741207697412076,
+      "grad_norm": 1.5040356499297907,
+      "learning_rate": 8.656051372020232e-06,
+      "loss": 1.1083,
+      "step": 367
+    },
+    {
+      "epoch": 0.9767750497677505,
+      "grad_norm": 1.5264462091802162,
+      "learning_rate": 8.648871125030576e-06,
+      "loss": 1.1647,
+      "step": 368
+    },
+    {
+      "epoch": 0.9794293297942933,
+      "grad_norm": 1.8183949324824284,
+      "learning_rate": 8.64167474348877e-06,
+      "loss": 1.0809,
+      "step": 369
+    },
+    {
+      "epoch": 0.9820836098208361,
+      "grad_norm": 2.6148655405710874,
+      "learning_rate": 8.634462259215719e-06,
+      "loss": 1.1195,
+      "step": 370
+    },
+    {
+      "epoch": 0.9847378898473789,
+      "grad_norm": 1.5140959417993884,
+      "learning_rate": 8.627233704103538e-06,
+      "loss": 1.0768,
+      "step": 371
+    },
+    {
+      "epoch": 0.9873921698739216,
+      "grad_norm": 1.3953146864224168,
+      "learning_rate": 8.619989110115398e-06,
+      "loss": 1.0998,
+      "step": 372
+    },
+    {
+      "epoch": 0.9900464499004645,
+      "grad_norm": 1.5342377987936564,
+      "learning_rate": 8.612728509285395e-06,
+      "loss": 1.1627,
+      "step": 373
+    },
+    {
+      "epoch": 0.9927007299270073,
+      "grad_norm": 1.6359257997310512,
+      "learning_rate": 8.6054519337184e-06,
+      "loss": 1.0947,
+      "step": 374
+    },
+    {
+      "epoch": 0.9953550099535501,
+      "grad_norm": 1.468781234700457,
+      "learning_rate": 8.59815941558992e-06,
+      "loss": 1.0958,
+      "step": 375
+    },
+    {
+      "epoch": 0.9980092899800929,
+      "grad_norm": 1.8585796860334978,
+      "learning_rate": 8.590850987145964e-06,
+      "loss": 1.1439,
+      "step": 376
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1504,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 376,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 357968545579008.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)