upload

.gitattributes

@@ -50,3 +50,4 @@ llmstream_results/qwen3_17b_base_streamline_slimpajama_prune10_start7/tokenizer.
 llmstream_results/qwen3_17b_base_streamline_slimpajama_prune4_start11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 llmstream_results/qwen3_17b_base_streamline_slimpajama_prune7_start10/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 llmstream_results/qwen25_7b_base_streamline_slimpajama_prune7_start13/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/tokenizer.json filter=lfs diff=lfs merge=lfs -text

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/config.json

@@ -0,0 +1,55 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "transformers_version": "4.57.6"
+}

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/lightweight_checkpoint_epoch_10/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:796b3e1017d6a2d796fabe10d48f33ef040add941b23ee460d0c05054416e299
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/lightweight_checkpoint_epoch_12/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed37b5a171b283f2f3af99cac7243c713e39fc82534b146fc54e9b12b8b62b67
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/lightweight_checkpoint_epoch_14/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f3c4607483682d14e0537ebe2a1679b671f256ca3884cc8501f972651c5488
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/lightweight_checkpoint_epoch_16/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b95adc29469a017154bf68c9815135d662bce00cb0540cc373317d47ad7c1ac
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/lightweight_checkpoint_epoch_18/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:157f77f76d3def581d20915422dd98332cb63ec8fefdf668747f82904e5ea4fb
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/lightweight_checkpoint_epoch_2/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11db89f66730d03740115079d574864a6604c872f03e35b7ee9388807ca8016d
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/lightweight_checkpoint_epoch_20/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f572fe38799d06bca46ebd0c228bf30e2dcedf15b4de91373db1df814674cb42
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/lightweight_checkpoint_epoch_4/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cda5c1ae8438c039df3d1ecabbb55c8b5ecbdcbb44eae93f2335771869c748a
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/lightweight_checkpoint_epoch_6/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9d66916064aa8a8005d419f1fe164b3001a9d78719922630c0bbbbf7350075
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/lightweight_checkpoint_epoch_8/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5b17e156b8404a5883105b9cb606d8b3fca5ebeec9cb0d55b1adb1e4773c731
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/lightweight_checkpoint_final/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f572fe38799d06bca46ebd0c228bf30e2dcedf15b4de91373db1df814674cb42
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37753d1c8dc943058221bf364c12695f6c2afafaa29b470af86d40ce0655e7a5
+size 4877660776

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a63d7b7037b97992e4ed5a58469680c01c1ddf5e68a6b95d3713d2172735e29
+size 4932751008

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4abbb5bde4be98f60df27813f0c8dcc23e88883766b858c9fe9881ca3e5629b3
+size 3556392240

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/model.safetensors.index.json

@@ -0,0 +1,299 @@
+{
+  "metadata": {
+    "total_parameters": 6683385344,
+    "total_size": 13366770688
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/run_args.txt

@@ -0,0 +1,9 @@
+git_commit=unknown
+dataset=slimpajama
+dataset_split=train
+collect_batch_size=8
+train_batch_size=16
+gradient_accumulation_step=16
+target_effective_batch=256
+command:
+python /workspace/here/abprune_update/compare_model/LLM-Streamline/qwen_mseloss_entry.py --model_name Qwen/Qwen2.5-7B --output_dir /workspace/here/abprune_update/results/qwen25_7b_base_streamline_slimpajama_prune4_start14 --dataset slimpajama --dataset_split train --layer_intervals 4 --best_layer 14 --cosine_num_data 300 --train_num_data 30000 --epoches 20 --batch_size 8 --collect_batch_size 8 --train_batch_size 16 --gradient_accumulation_step 16 --lr 1e-5 --min_lr 5e-5 --wd 1e-3 

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune4_start14/train_loss.txt

@@ -0,0 +1,376 @@
+# Train loss logged every 100 global steps
+epoch=0 global_step=100 optimizer_step=6 loss=0.6280246973
+epoch=0 global_step=200 optimizer_step=12 loss=0.5955747366
+epoch=0 global_step=300 optimizer_step=18 loss=0.6060288548
+epoch=0 global_step=400 optimizer_step=24 loss=0.6061494350
+epoch=0 global_step=500 optimizer_step=31 loss=0.5946739316
+epoch=0 global_step=600 optimizer_step=37 loss=0.5899985433
+epoch=0 global_step=700 optimizer_step=43 loss=0.5890384912
+epoch=0 global_step=800 optimizer_step=49 loss=0.5824890137
+epoch=0 global_step=900 optimizer_step=56 loss=0.5875536203
+epoch=0 global_step=1000 optimizer_step=62 loss=0.6069180369
+epoch=0 global_step=1100 optimizer_step=68 loss=0.5818557143
+epoch=0 global_step=1200 optimizer_step=74 loss=0.5709612370
+epoch=0 global_step=1300 optimizer_step=81 loss=0.5807784796
+epoch=0 global_step=1400 optimizer_step=87 loss=0.5723325610
+epoch=0 global_step=1500 optimizer_step=93 loss=0.5724815726
+epoch=0 global_step=1600 optimizer_step=99 loss=0.5464488268
+epoch=0 global_step=1700 optimizer_step=106 loss=0.5413125157
+epoch=0 global_step=1800 optimizer_step=112 loss=0.5358296633
+epoch=1 global_step=1900 optimizer_step=118 loss=0.5423967838
+epoch=1 global_step=2000 optimizer_step=124 loss=0.5313861966
+epoch=1 global_step=2100 optimizer_step=131 loss=0.5264801383
+epoch=1 global_step=2200 optimizer_step=137 loss=0.5099952221
+epoch=1 global_step=2300 optimizer_step=143 loss=0.5233259201
+epoch=1 global_step=2400 optimizer_step=149 loss=0.5282754302
+epoch=1 global_step=2500 optimizer_step=156 loss=0.4946201444
+epoch=1 global_step=2600 optimizer_step=162 loss=0.5350471139
+epoch=1 global_step=2700 optimizer_step=168 loss=0.4996516705
+epoch=1 global_step=2800 optimizer_step=174 loss=0.5030059218
+epoch=1 global_step=2900 optimizer_step=181 loss=0.4874012768
+epoch=1 global_step=3000 optimizer_step=187 loss=0.4770377576
+epoch=1 global_step=3100 optimizer_step=193 loss=0.4862224162
+epoch=1 global_step=3200 optimizer_step=199 loss=0.4824700952
+epoch=1 global_step=3300 optimizer_step=206 loss=0.4848408997
+epoch=1 global_step=3400 optimizer_step=212 loss=0.4700763524
+epoch=1 global_step=3500 optimizer_step=218 loss=0.4555876553
+epoch=1 global_step=3600 optimizer_step=224 loss=0.4795846343
+epoch=1 global_step=3700 optimizer_step=231 loss=0.4717085958
+epoch=2 global_step=3800 optimizer_step=237 loss=0.4667043984
+epoch=2 global_step=3900 optimizer_step=243 loss=0.4737735987
+epoch=2 global_step=4000 optimizer_step=249 loss=0.4563411474
+epoch=2 global_step=4100 optimizer_step=255 loss=0.4543725848
+epoch=2 global_step=4200 optimizer_step=262 loss=0.4502072632
+epoch=2 global_step=4300 optimizer_step=268 loss=0.4392034113
+epoch=2 global_step=4400 optimizer_step=274 loss=0.4447955489
+epoch=2 global_step=4500 optimizer_step=280 loss=0.4362468719
+epoch=2 global_step=4600 optimizer_step=287 loss=0.4438058436
+epoch=2 global_step=4700 optimizer_step=293 loss=0.4284437299
+epoch=2 global_step=4800 optimizer_step=299 loss=0.4307835102
+epoch=2 global_step=4900 optimizer_step=305 loss=0.4418677092
+epoch=2 global_step=5000 optimizer_step=312 loss=0.4537254274
+epoch=2 global_step=5100 optimizer_step=318 loss=0.4553131461
+epoch=2 global_step=5200 optimizer_step=324 loss=0.4429836571
+epoch=2 global_step=5300 optimizer_step=330 loss=0.4631663263
+epoch=2 global_step=5400 optimizer_step=337 loss=0.4120984674
+epoch=2 global_step=5500 optimizer_step=343 loss=0.4157412350
+epoch=2 global_step=5600 optimizer_step=349 loss=0.4255400002
+epoch=3 global_step=5700 optimizer_step=355 loss=0.4183127582
+epoch=3 global_step=5800 optimizer_step=361 loss=0.4101392329
+epoch=3 global_step=5900 optimizer_step=368 loss=0.4121729434
+epoch=3 global_step=6000 optimizer_step=374 loss=0.4226918519
+epoch=3 global_step=6100 optimizer_step=380 loss=0.4047755301
+epoch=3 global_step=6200 optimizer_step=386 loss=0.4186348021
+epoch=3 global_step=6300 optimizer_step=393 loss=0.4635231495
+epoch=3 global_step=6400 optimizer_step=399 loss=0.4060579240
+epoch=3 global_step=6500 optimizer_step=405 loss=0.4048015475
+epoch=3 global_step=6600 optimizer_step=411 loss=0.4102056324
+epoch=3 global_step=6700 optimizer_step=418 loss=0.4065847099
+epoch=3 global_step=6800 optimizer_step=424 loss=0.3967223465
+epoch=3 global_step=6900 optimizer_step=430 loss=0.4072639048
+epoch=3 global_step=7000 optimizer_step=436 loss=0.3987608254
+epoch=3 global_step=7100 optimizer_step=443 loss=0.4214629233
+epoch=3 global_step=7200 optimizer_step=449 loss=0.3712688684
+epoch=3 global_step=7300 optimizer_step=455 loss=0.3877851367
+epoch=3 global_step=7400 optimizer_step=461 loss=0.4014923275
+epoch=3 global_step=7500 optimizer_step=468 loss=0.4003686309
+epoch=4 global_step=7600 optimizer_step=474 loss=0.3978938460
+epoch=4 global_step=7700 optimizer_step=480 loss=0.3955855966
+epoch=4 global_step=7800 optimizer_step=486 loss=0.3976813555
+epoch=4 global_step=7900 optimizer_step=492 loss=0.3937265575
+epoch=4 global_step=8000 optimizer_step=499 loss=0.3806566596
+epoch=4 global_step=8100 optimizer_step=505 loss=0.4275156856
+epoch=4 global_step=8200 optimizer_step=511 loss=0.3892246187
+epoch=4 global_step=8300 optimizer_step=517 loss=0.3984976709
+epoch=4 global_step=8400 optimizer_step=524 loss=0.4176390767
+epoch=4 global_step=8500 optimizer_step=530 loss=0.3908779919
+epoch=4 global_step=8600 optimizer_step=536 loss=0.3828011751
+epoch=4 global_step=8700 optimizer_step=542 loss=0.3878531754
+epoch=4 global_step=8800 optimizer_step=549 loss=0.3946472704
+epoch=4 global_step=8900 optimizer_step=555 loss=0.3837918639
+epoch=4 global_step=9000 optimizer_step=561 loss=0.3922686875
+epoch=4 global_step=9100 optimizer_step=567 loss=0.3912540376
+epoch=4 global_step=9200 optimizer_step=574 loss=0.3650941551
+epoch=4 global_step=9300 optimizer_step=580 loss=0.3916602731
+epoch=5 global_step=9400 optimizer_step=586 loss=0.3817123175
+epoch=5 global_step=9500 optimizer_step=592 loss=0.3940964639
+epoch=5 global_step=9600 optimizer_step=599 loss=0.3729894757
+epoch=5 global_step=9700 optimizer_step=605 loss=0.3936273456
+epoch=5 global_step=9800 optimizer_step=611 loss=0.3705169857
+epoch=5 global_step=9900 optimizer_step=617 loss=0.3862195313
+epoch=5 global_step=10000 optimizer_step=624 loss=0.3697868288
+epoch=5 global_step=10100 optimizer_step=630 loss=0.3777401745
+epoch=5 global_step=10200 optimizer_step=636 loss=0.3887447119
+epoch=5 global_step=10300 optimizer_step=642 loss=0.3672959507
+epoch=5 global_step=10400 optimizer_step=649 loss=0.3806643784
+epoch=5 global_step=10500 optimizer_step=655 loss=0.3802758157
+epoch=5 global_step=10600 optimizer_step=661 loss=0.3705605268
+epoch=5 global_step=10700 optimizer_step=667 loss=0.3840993047
+epoch=5 global_step=10800 optimizer_step=674 loss=0.3694220781
+epoch=5 global_step=10900 optimizer_step=680 loss=0.3750492334
+epoch=5 global_step=11000 optimizer_step=686 loss=0.3897678256
+epoch=5 global_step=11100 optimizer_step=692 loss=0.3756435513
+epoch=5 global_step=11200 optimizer_step=699 loss=0.4047976732
+epoch=6 global_step=11300 optimizer_step=705 loss=0.3682834804
+epoch=6 global_step=11400 optimizer_step=711 loss=0.3716787994
+epoch=6 global_step=11500 optimizer_step=717 loss=0.3765583336
+epoch=6 global_step=11600 optimizer_step=723 loss=0.3985634744
+epoch=6 global_step=11700 optimizer_step=730 loss=0.3711325228
+epoch=6 global_step=11800 optimizer_step=736 loss=0.3954555094
+epoch=6 global_step=11900 optimizer_step=742 loss=0.3603337109
+epoch=6 global_step=12000 optimizer_step=748 loss=0.3717476428
+epoch=6 global_step=12100 optimizer_step=755 loss=0.3593377471
+epoch=6 global_step=12200 optimizer_step=761 loss=0.3590532839
+epoch=6 global_step=12300 optimizer_step=767 loss=0.3658397794
+epoch=6 global_step=12400 optimizer_step=773 loss=0.3664589226
+epoch=6 global_step=12500 optimizer_step=780 loss=0.3576475084
+epoch=6 global_step=12600 optimizer_step=786 loss=0.3538082242
+epoch=6 global_step=12700 optimizer_step=792 loss=0.3608756363
+epoch=6 global_step=12800 optimizer_step=798 loss=0.3636160791
+epoch=6 global_step=12900 optimizer_step=805 loss=0.3741783202
+epoch=6 global_step=13000 optimizer_step=811 loss=0.3486209810
+epoch=6 global_step=13100 optimizer_step=817 loss=0.3748822808
+epoch=7 global_step=13200 optimizer_step=823 loss=0.3532798886
+epoch=7 global_step=13300 optimizer_step=829 loss=0.3593154252
+epoch=7 global_step=13400 optimizer_step=836 loss=0.3473418951
+epoch=7 global_step=13500 optimizer_step=842 loss=0.3531731665
+epoch=7 global_step=13600 optimizer_step=848 loss=0.3349471390
+epoch=7 global_step=13700 optimizer_step=854 loss=0.3675399423
+epoch=7 global_step=13800 optimizer_step=861 loss=0.3498092592
+epoch=7 global_step=13900 optimizer_step=867 loss=0.3810647130
+epoch=7 global_step=14000 optimizer_step=873 loss=0.3621548414
+epoch=7 global_step=14100 optimizer_step=879 loss=0.3417578042
+epoch=7 global_step=14200 optimizer_step=886 loss=0.3723480403
+epoch=7 global_step=14300 optimizer_step=892 loss=0.3679147959
+epoch=7 global_step=14400 optimizer_step=898 loss=0.3628216088
+epoch=7 global_step=14500 optimizer_step=904 loss=0.3434636295
+epoch=7 global_step=14600 optimizer_step=911 loss=0.3389690518
+epoch=7 global_step=14700 optimizer_step=917 loss=0.3421244025
+epoch=7 global_step=14800 optimizer_step=923 loss=0.3656879961
+epoch=7 global_step=14900 optimizer_step=929 loss=0.3354720771
+epoch=7 global_step=15000 optimizer_step=936 loss=0.3627282679
+epoch=8 global_step=15100 optimizer_step=942 loss=0.3466354609
+epoch=8 global_step=15200 optimizer_step=948 loss=0.3367359340
+epoch=8 global_step=15300 optimizer_step=954 loss=0.3489125967
+epoch=8 global_step=15400 optimizer_step=960 loss=0.3605472445
+epoch=8 global_step=15500 optimizer_step=967 loss=0.3399795294
+epoch=8 global_step=15600 optimizer_step=973 loss=0.3559940755
+epoch=8 global_step=15700 optimizer_step=979 loss=0.3643562198
+epoch=8 global_step=15800 optimizer_step=985 loss=0.3505872786
+epoch=8 global_step=15900 optimizer_step=992 loss=0.3341229856
+epoch=8 global_step=16000 optimizer_step=998 loss=0.3332912028
+epoch=8 global_step=16100 optimizer_step=1004 loss=0.3452818096
+epoch=8 global_step=16200 optimizer_step=1010 loss=0.3288953006
+epoch=8 global_step=16300 optimizer_step=1017 loss=0.3378151655
+epoch=8 global_step=16400 optimizer_step=1023 loss=0.3343669474
+epoch=8 global_step=16500 optimizer_step=1029 loss=0.3342168927
+epoch=8 global_step=16600 optimizer_step=1035 loss=0.3450803459
+epoch=8 global_step=16700 optimizer_step=1042 loss=0.3558592200
+epoch=8 global_step=16800 optimizer_step=1048 loss=0.3419162035
+epoch=9 global_step=16900 optimizer_step=1054 loss=0.3552534282
+epoch=9 global_step=17000 optimizer_step=1060 loss=0.3621034920
+epoch=9 global_step=17100 optimizer_step=1067 loss=0.3365733325
+epoch=9 global_step=17200 optimizer_step=1073 loss=0.3426264524
+epoch=9 global_step=17300 optimizer_step=1079 loss=0.3425265253
+epoch=9 global_step=17400 optimizer_step=1085 loss=0.3269275427
+epoch=9 global_step=17500 optimizer_step=1092 loss=0.3608968854
+epoch=9 global_step=17600 optimizer_step=1098 loss=0.3427681625
+epoch=9 global_step=17700 optimizer_step=1104 loss=0.3409635723
+epoch=9 global_step=17800 optimizer_step=1110 loss=0.3487356901
+epoch=9 global_step=17900 optimizer_step=1117 loss=0.3503099382
+epoch=9 global_step=18000 optimizer_step=1123 loss=0.3137445152
+epoch=9 global_step=18100 optimizer_step=1129 loss=0.3165184855
+epoch=9 global_step=18200 optimizer_step=1135 loss=0.3404249549
+epoch=9 global_step=18300 optimizer_step=1142 loss=0.3305064738
+epoch=9 global_step=18400 optimizer_step=1148 loss=0.3213821948
+epoch=9 global_step=18500 optimizer_step=1154 loss=0.3563238680
+epoch=9 global_step=18600 optimizer_step=1160 loss=0.3261624277
+epoch=9 global_step=18700 optimizer_step=1167 loss=0.3417434096
+epoch=10 global_step=18800 optimizer_step=1173 loss=0.3324816823
+epoch=10 global_step=18900 optimizer_step=1179 loss=0.3236729205
+epoch=10 global_step=19000 optimizer_step=1185 loss=0.3310209811
+epoch=10 global_step=19100 optimizer_step=1191 loss=0.3362703621
+epoch=10 global_step=19200 optimizer_step=1198 loss=0.3510300219
+epoch=10 global_step=19300 optimizer_step=1204 loss=0.3044082522
+epoch=10 global_step=19400 optimizer_step=1210 loss=0.3315805793
+epoch=10 global_step=19500 optimizer_step=1216 loss=0.3180167377
+epoch=10 global_step=19600 optimizer_step=1223 loss=0.3373995721
+epoch=10 global_step=19700 optimizer_step=1229 loss=0.3427487314
+epoch=10 global_step=19800 optimizer_step=1235 loss=0.3351587057
+epoch=10 global_step=19900 optimizer_step=1241 loss=0.3210649192
+epoch=10 global_step=20000 optimizer_step=1248 loss=0.3643464446
+epoch=10 global_step=20100 optimizer_step=1254 loss=0.3272065520
+epoch=10 global_step=20200 optimizer_step=1260 loss=0.3464365304
+epoch=10 global_step=20300 optimizer_step=1266 loss=0.3297417760
+epoch=10 global_step=20400 optimizer_step=1273 loss=0.3309115171
+epoch=10 global_step=20500 optimizer_step=1279 loss=0.3534500301
+epoch=10 global_step=20600 optimizer_step=1285 loss=0.3124379218
+epoch=11 global_step=20700 optimizer_step=1291 loss=0.3398695886
+epoch=11 global_step=20800 optimizer_step=1297 loss=0.3166249692
+epoch=11 global_step=20900 optimizer_step=1304 loss=0.3410923183
+epoch=11 global_step=21000 optimizer_step=1310 loss=0.3313598633
+epoch=11 global_step=21100 optimizer_step=1316 loss=0.3301827610
+epoch=11 global_step=21200 optimizer_step=1322 loss=0.3135031462
+epoch=11 global_step=21300 optimizer_step=1329 loss=0.3289923668
+epoch=11 global_step=21400 optimizer_step=1335 loss=0.3196567297
+epoch=11 global_step=21500 optimizer_step=1341 loss=0.3303555250
+epoch=11 global_step=21600 optimizer_step=1347 loss=0.3300252557
+epoch=11 global_step=21700 optimizer_step=1354 loss=0.3146325648
+epoch=11 global_step=21800 optimizer_step=1360 loss=0.3130807877
+epoch=11 global_step=21900 optimizer_step=1366 loss=0.3277018964
+epoch=11 global_step=22000 optimizer_step=1372 loss=0.3317243159
+epoch=11 global_step=22100 optimizer_step=1379 loss=0.3335621953
+epoch=11 global_step=22200 optimizer_step=1385 loss=0.3279343545
+epoch=11 global_step=22300 optimizer_step=1391 loss=0.3231457770
+epoch=11 global_step=22400 optimizer_step=1397 loss=0.3241300285
+epoch=11 global_step=22500 optimizer_step=1404 loss=0.3204368353
+epoch=12 global_step=22600 optimizer_step=1410 loss=0.3445186019
+epoch=12 global_step=22700 optimizer_step=1416 loss=0.3221963644
+epoch=12 global_step=22800 optimizer_step=1422 loss=0.3254996240
+epoch=12 global_step=22900 optimizer_step=1428 loss=0.3245154321
+epoch=12 global_step=23000 optimizer_step=1435 loss=0.3305420578
+epoch=12 global_step=23100 optimizer_step=1441 loss=0.3415921330
+epoch=12 global_step=23200 optimizer_step=1447 loss=0.3211146295
+epoch=12 global_step=23300 optimizer_step=1453 loss=0.3128828406
+epoch=12 global_step=23400 optimizer_step=1460 loss=0.3153214455
+epoch=12 global_step=23500 optimizer_step=1466 loss=0.3407448828
+epoch=12 global_step=23600 optimizer_step=1472 loss=0.3531779647
+epoch=12 global_step=23700 optimizer_step=1478 loss=0.3329178989
+epoch=12 global_step=23800 optimizer_step=1485 loss=0.3152965605
+epoch=12 global_step=23900 optimizer_step=1491 loss=0.3271707892
+epoch=12 global_step=24000 optimizer_step=1497 loss=0.3276931643
+epoch=12 global_step=24100 optimizer_step=1503 loss=0.3163952827
+epoch=12 global_step=24200 optimizer_step=1510 loss=0.3177058101
+epoch=12 global_step=24300 optimizer_step=1516 loss=0.3322078288
+epoch=13 global_step=24400 optimizer_step=1522 loss=0.3339844048
+epoch=13 global_step=24500 optimizer_step=1528 loss=0.3119676709
+epoch=13 global_step=24600 optimizer_step=1535 loss=0.3268762231
+epoch=13 global_step=24700 optimizer_step=1541 loss=0.3187038004
+epoch=13 global_step=24800 optimizer_step=1547 loss=0.3362709582
+epoch=13 global_step=24900 optimizer_step=1553 loss=0.3353601694
+epoch=13 global_step=25000 optimizer_step=1560 loss=0.3327917159
+epoch=13 global_step=25100 optimizer_step=1566 loss=0.3370052576
+epoch=13 global_step=25200 optimizer_step=1572 loss=0.3181844652
+epoch=13 global_step=25300 optimizer_step=1578 loss=0.3260912001
+epoch=13 global_step=25400 optimizer_step=1585 loss=0.3212134242
+epoch=13 global_step=25500 optimizer_step=1591 loss=0.3282074332
+epoch=13 global_step=25600 optimizer_step=1597 loss=0.3130615950
+epoch=13 global_step=25700 optimizer_step=1603 loss=0.3160154819
+epoch=13 global_step=25800 optimizer_step=1610 loss=0.3286188841
+epoch=13 global_step=25900 optimizer_step=1616 loss=0.3188516200
+epoch=13 global_step=26000 optimizer_step=1622 loss=0.3142136335
+epoch=13 global_step=26100 optimizer_step=1628 loss=0.3150956333
+epoch=13 global_step=26200 optimizer_step=1635 loss=0.2970572114
+epoch=14 global_step=26300 optimizer_step=1641 loss=0.3091490865
+epoch=14 global_step=26400 optimizer_step=1647 loss=0.3129461706
+epoch=14 global_step=26500 optimizer_step=1653 loss=0.3131989241
+epoch=14 global_step=26600 optimizer_step=1659 loss=0.3332104087
+epoch=14 global_step=26700 optimizer_step=1666 loss=0.3341191411
+epoch=14 global_step=26800 optimizer_step=1672 loss=0.3204402328
+epoch=14 global_step=26900 optimizer_step=1678 loss=0.3144182861
+epoch=14 global_step=27000 optimizer_step=1684 loss=0.3146705627
+epoch=14 global_step=27100 optimizer_step=1691 loss=0.3274834752
+epoch=14 global_step=27200 optimizer_step=1697 loss=0.3165425360
+epoch=14 global_step=27300 optimizer_step=1703 loss=0.3271869421
+epoch=14 global_step=27400 optimizer_step=1709 loss=0.3205596209
+epoch=14 global_step=27500 optimizer_step=1716 loss=0.3039746881
+epoch=14 global_step=27600 optimizer_step=1722 loss=0.3190364540
+epoch=14 global_step=27700 optimizer_step=1728 loss=0.3302094638
+epoch=14 global_step=27800 optimizer_step=1734 loss=0.2840362489
+epoch=14 global_step=27900 optimizer_step=1741 loss=0.3199813962
+epoch=14 global_step=28000 optimizer_step=1747 loss=0.3123193681
+epoch=14 global_step=28100 optimizer_step=1753 loss=0.3206653595
+epoch=15 global_step=28200 optimizer_step=1759 loss=0.2989029288
+epoch=15 global_step=28300 optimizer_step=1765 loss=0.2927998304
+epoch=15 global_step=28400 optimizer_step=1772 loss=0.3097549379
+epoch=15 global_step=28500 optimizer_step=1778 loss=0.3094291091
+epoch=15 global_step=28600 optimizer_step=1784 loss=0.3332622945
+epoch=15 global_step=28700 optimizer_step=1790 loss=0.3154140413
+epoch=15 global_step=28800 optimizer_step=1797 loss=0.3263406754
+epoch=15 global_step=28900 optimizer_step=1803 loss=0.3043159544
+epoch=15 global_step=29000 optimizer_step=1809 loss=0.3251839578
+epoch=15 global_step=29100 optimizer_step=1815 loss=0.3016368747
+epoch=15 global_step=29200 optimizer_step=1822 loss=0.3250820637
+epoch=15 global_step=29300 optimizer_step=1828 loss=0.3024235666
+epoch=15 global_step=29400 optimizer_step=1834 loss=0.3297625482
+epoch=15 global_step=29500 optimizer_step=1840 loss=0.3288254738
+epoch=15 global_step=29600 optimizer_step=1847 loss=0.3125196695
+epoch=15 global_step=29700 optimizer_step=1853 loss=0.3183090389
+epoch=15 global_step=29800 optimizer_step=1859 loss=0.3046091199
+epoch=15 global_step=29900 optimizer_step=1865 loss=0.2772753239
+epoch=15 global_step=30000 optimizer_step=1872 loss=0.2986568213
+epoch=16 global_step=30100 optimizer_step=1878 loss=0.3215775490
+epoch=16 global_step=30200 optimizer_step=1884 loss=0.2987703681
+epoch=16 global_step=30300 optimizer_step=1890 loss=0.3143559992
+epoch=16 global_step=30400 optimizer_step=1896 loss=0.3108182549
+epoch=16 global_step=30500 optimizer_step=1903 loss=0.3098469675
+epoch=16 global_step=30600 optimizer_step=1909 loss=0.3144239187
+epoch=16 global_step=30700 optimizer_step=1915 loss=0.3046638072
+epoch=16 global_step=30800 optimizer_step=1921 loss=0.3060043752
+epoch=16 global_step=30900 optimizer_step=1928 loss=0.3025161922
+epoch=16 global_step=31000 optimizer_step=1934 loss=0.2972372174
+epoch=16 global_step=31100 optimizer_step=1940 loss=0.3153733015
+epoch=16 global_step=31200 optimizer_step=1946 loss=0.3169239461
+epoch=16 global_step=31300 optimizer_step=1953 loss=0.2864927649
+epoch=16 global_step=31400 optimizer_step=1959 loss=0.2854681015
+epoch=16 global_step=31500 optimizer_step=1965 loss=0.3253777921
+epoch=16 global_step=31600 optimizer_step=1971 loss=0.3093199134
+epoch=16 global_step=31700 optimizer_step=1978 loss=0.3068638742
+epoch=16 global_step=31800 optimizer_step=1984 loss=0.3173825443
+epoch=17 global_step=31900 optimizer_step=1990 loss=0.3135136068
+epoch=17 global_step=32000 optimizer_step=1996 loss=0.3073872626
+epoch=17 global_step=32100 optimizer_step=2003 loss=0.3072496355
+epoch=17 global_step=32200 optimizer_step=2009 loss=0.2972587645
+epoch=17 global_step=32300 optimizer_step=2015 loss=0.3117443621
+epoch=17 global_step=32400 optimizer_step=2021 loss=0.3245603442
+epoch=17 global_step=32500 optimizer_step=2028 loss=0.2904153466
+epoch=17 global_step=32600 optimizer_step=2034 loss=0.2941939831
+epoch=17 global_step=32700 optimizer_step=2040 loss=0.3146495223
+epoch=17 global_step=32800 optimizer_step=2046 loss=0.2998766899
+epoch=17 global_step=32900 optimizer_step=2053 loss=0.2970530689
+epoch=17 global_step=33000 optimizer_step=2059 loss=0.3086760640
+epoch=17 global_step=33100 optimizer_step=2065 loss=0.2951708734
+epoch=17 global_step=33200 optimizer_step=2071 loss=0.3165977001
+epoch=17 global_step=33300 optimizer_step=2078 loss=0.3146648407
+epoch=17 global_step=33400 optimizer_step=2084 loss=0.3148266375
+epoch=17 global_step=33500 optimizer_step=2090 loss=0.3028717041
+epoch=17 global_step=33600 optimizer_step=2096 loss=0.3020756841
+epoch=17 global_step=33700 optimizer_step=2103 loss=0.3106534183
+epoch=18 global_step=33800 optimizer_step=2109 loss=0.2961339355
+epoch=18 global_step=33900 optimizer_step=2115 loss=0.2874774933
+epoch=18 global_step=34000 optimizer_step=2121 loss=0.3135649860
+epoch=18 global_step=34100 optimizer_step=2127 loss=0.2991551757
+epoch=18 global_step=34200 optimizer_step=2134 loss=0.3042080402
+epoch=18 global_step=34300 optimizer_step=2140 loss=0.3163394928
+epoch=18 global_step=34400 optimizer_step=2146 loss=0.2850480676
+epoch=18 global_step=34500 optimizer_step=2152 loss=0.3124726415
+epoch=18 global_step=34600 optimizer_step=2159 loss=0.3123888373
+epoch=18 global_step=34700 optimizer_step=2165 loss=0.3184139132
+epoch=18 global_step=34800 optimizer_step=2171 loss=0.2881664634
+epoch=18 global_step=34900 optimizer_step=2177 loss=0.3110211492
+epoch=18 global_step=35000 optimizer_step=2184 loss=0.2964107096
+epoch=18 global_step=35100 optimizer_step=2190 loss=0.3123877645
+epoch=18 global_step=35200 optimizer_step=2196 loss=0.3064133823
+epoch=18 global_step=35300 optimizer_step=2202 loss=0.2930601537
+epoch=18 global_step=35400 optimizer_step=2209 loss=0.3096895218
+epoch=18 global_step=35500 optimizer_step=2215 loss=0.2939477861
+epoch=18 global_step=35600 optimizer_step=2221 loss=0.3021473885
+epoch=19 global_step=35700 optimizer_step=2227 loss=0.3063790500
+epoch=19 global_step=35800 optimizer_step=2233 loss=0.2828170359
+epoch=19 global_step=35900 optimizer_step=2240 loss=0.2953545749
+epoch=19 global_step=36000 optimizer_step=2246 loss=0.2941749096
+epoch=19 global_step=36100 optimizer_step=2252 loss=0.2874402702
+epoch=19 global_step=36200 optimizer_step=2258 loss=0.2951750755
+epoch=19 global_step=36300 optimizer_step=2265 loss=0.2841731608
+epoch=19 global_step=36400 optimizer_step=2271 loss=0.3075576723
+epoch=19 global_step=36500 optimizer_step=2277 loss=0.2906816006
+epoch=19 global_step=36600 optimizer_step=2283 loss=0.2915522456
+epoch=19 global_step=36700 optimizer_step=2290 loss=0.3136820793
+epoch=19 global_step=36800 optimizer_step=2296 loss=0.2958547175
+epoch=19 global_step=36900 optimizer_step=2302 loss=0.3065222502
+epoch=19 global_step=37000 optimizer_step=2308 loss=0.2987833619
+epoch=19 global_step=37100 optimizer_step=2315 loss=0.3065221906
+epoch=19 global_step=37200 optimizer_step=2321 loss=0.3112783134
+epoch=19 global_step=37300 optimizer_step=2327 loss=0.2949294746
+epoch=19 global_step=37400 optimizer_step=2333 loss=0.2960310876
+epoch=19 global_step=37500 optimizer_step=2340 loss=0.2956009805