upload

.gitattributes

@@ -49,3 +49,4 @@ llmstream_results/llama31_8b_base_streamline_slimpajama_prune8_start22/tokenizer
 llmstream_results/qwen3_17b_base_streamline_slimpajama_prune10_start7/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 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_prune7_start13/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_prune7_start13/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_prune7_start13/config.json

@@ -0,0 +1,52 @@
+{
+  "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"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 21,
+  "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_prune7_start13/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_prune7_start13/lightweight_checkpoint_epoch_10/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03cff2e3f1a679680de749a8955395ce2e828cd4a4c539cd93e0b5b4c268f293
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune7_start13/lightweight_checkpoint_epoch_12/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e0220dbb85431e3b59e9419b84e8115cbb43ac3f827226b82058c6c48ed816c
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune7_start13/lightweight_checkpoint_epoch_14/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d080fe8386539bc1dc5aeed5b9ceeafb00815c1cca67b912be72b8c8d8f2f23
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune7_start13/lightweight_checkpoint_epoch_16/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:445e495751afa67e06d03c4ca1f8d8ac2d0373074ccf4188c67f8cd10b3ddbc7
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune7_start13/lightweight_checkpoint_epoch_18/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c575381108ded5c32678cba942dda100c6c3a25fd3b1029e8546e8aa7df168f0
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune7_start13/lightweight_checkpoint_epoch_2/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87252ee6a42d4e2c9d249fee0cf6f15ac86b0714c39c2ab0adc285ea7e481c32
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune7_start13/lightweight_checkpoint_epoch_20/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc98c12f387d027e51da54716794398c0f5a481ea271e2251c6e9954a6ab3784
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune7_start13/lightweight_checkpoint_epoch_4/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a5bad1506fb3e71b8dcb21cb46ff1a0486c49d39e458c9615e4c0655812fb67
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune7_start13/lightweight_checkpoint_epoch_6/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd3e01d6548cd7e524d69116d30e0a16e7dfe022229e072980f6460efe8de373
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune7_start13/lightweight_checkpoint_epoch_8/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920a203d1a411997a4d5edd5b088845566a077b415d4cf66d2bc2321134f3bd3
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune7_start13/lightweight_checkpoint_final/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc98c12f387d027e51da54716794398c0f5a481ea271e2251c6e9954a6ab3784
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune7_start13/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_prune7_start13/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bba0db3e087fcd5ec608e0b7d89de6857a231b1a3a25f036d53d12c2e74231ab
+size 4932751008

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune7_start13/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e90edf32226d2c829f80eede1bf3f204871a2a22ae802f4b2fac3bd7b70a5d4
+size 2158041344

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune7_start13/model.safetensors.index.json

@@ -0,0 +1,263 @@
+{
+  "metadata": {
+    "total_parameters": 5984211968,
+    "total_size": 11968423936
+  },
+  "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.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_prune7_start13/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_prune7_start13 --dataset slimpajama --dataset_split train --layer_intervals 7 --best_layer 13 --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_prune7_start13/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_prune7_start13/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_prune7_start13/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_prune7_start13/train_loss.txt

@@ -0,0 +1,376 @@
+# Train loss logged every 100 global steps
+epoch=0 global_step=100 optimizer_step=6 loss=2.3540856838
+epoch=0 global_step=200 optimizer_step=12 loss=2.2857241631
+epoch=0 global_step=300 optimizer_step=18 loss=2.2648389339
+epoch=0 global_step=400 optimizer_step=24 loss=2.2430224419
+epoch=0 global_step=500 optimizer_step=31 loss=2.2566947937
+epoch=0 global_step=600 optimizer_step=37 loss=2.1911501884
+epoch=0 global_step=700 optimizer_step=43 loss=2.1505384445
+epoch=0 global_step=800 optimizer_step=49 loss=2.2134490013
+epoch=0 global_step=900 optimizer_step=56 loss=2.2204935551
+epoch=0 global_step=1000 optimizer_step=62 loss=2.1479070187
+epoch=0 global_step=1100 optimizer_step=68 loss=2.0994341373
+epoch=0 global_step=1200 optimizer_step=74 loss=2.1499974728
+epoch=0 global_step=1300 optimizer_step=81 loss=2.1152188778
+epoch=0 global_step=1400 optimizer_step=87 loss=2.0646119118
+epoch=0 global_step=1500 optimizer_step=93 loss=2.0435640812
+epoch=0 global_step=1600 optimizer_step=99 loss=2.0184891224
+epoch=0 global_step=1700 optimizer_step=106 loss=2.0854606628
+epoch=0 global_step=1800 optimizer_step=112 loss=1.9178805351
+epoch=1 global_step=1900 optimizer_step=118 loss=2.0645971298
+epoch=1 global_step=2000 optimizer_step=124 loss=2.0038316250
+epoch=1 global_step=2100 optimizer_step=131 loss=1.8867623806
+epoch=1 global_step=2200 optimizer_step=137 loss=1.8500891924
+epoch=1 global_step=2300 optimizer_step=143 loss=1.8975088596
+epoch=1 global_step=2400 optimizer_step=149 loss=1.8278379440
+epoch=1 global_step=2500 optimizer_step=156 loss=1.8746354580
+epoch=1 global_step=2600 optimizer_step=162 loss=1.7898093462
+epoch=1 global_step=2700 optimizer_step=168 loss=1.7157006264
+epoch=1 global_step=2800 optimizer_step=174 loss=1.7785683870
+epoch=1 global_step=2900 optimizer_step=181 loss=1.7219825983
+epoch=1 global_step=3000 optimizer_step=187 loss=1.6930490732
+epoch=1 global_step=3100 optimizer_step=193 loss=1.7138446569
+epoch=1 global_step=3200 optimizer_step=199 loss=1.7071021795
+epoch=1 global_step=3300 optimizer_step=206 loss=1.7007300854
+epoch=1 global_step=3400 optimizer_step=212 loss=1.6636472940
+epoch=1 global_step=3500 optimizer_step=218 loss=1.6242893934
+epoch=1 global_step=3600 optimizer_step=224 loss=1.6418223381
+epoch=1 global_step=3700 optimizer_step=231 loss=1.5903137922
+epoch=2 global_step=3800 optimizer_step=237 loss=1.6745876074
+epoch=2 global_step=3900 optimizer_step=243 loss=1.5321444273
+epoch=2 global_step=4000 optimizer_step=249 loss=1.6283562183
+epoch=2 global_step=4100 optimizer_step=255 loss=1.5424456596
+epoch=2 global_step=4200 optimizer_step=262 loss=1.5795130730
+epoch=2 global_step=4300 optimizer_step=268 loss=1.5748940706
+epoch=2 global_step=4400 optimizer_step=274 loss=1.5649579763
+epoch=2 global_step=4500 optimizer_step=280 loss=1.5309313536
+epoch=2 global_step=4600 optimizer_step=287 loss=1.5006035566
+epoch=2 global_step=4700 optimizer_step=293 loss=1.5824619532
+epoch=2 global_step=4800 optimizer_step=299 loss=1.5179753304
+epoch=2 global_step=4900 optimizer_step=305 loss=1.5187071562
+epoch=2 global_step=5000 optimizer_step=312 loss=1.4617792368
+epoch=2 global_step=5100 optimizer_step=318 loss=1.5073635578
+epoch=2 global_step=5200 optimizer_step=324 loss=1.5715391636
+epoch=2 global_step=5300 optimizer_step=330 loss=1.4789936543
+epoch=2 global_step=5400 optimizer_step=337 loss=1.4578340054
+epoch=2 global_step=5500 optimizer_step=343 loss=1.4957518578
+epoch=2 global_step=5600 optimizer_step=349 loss=1.4794688225
+epoch=3 global_step=5700 optimizer_step=355 loss=1.4870343208
+epoch=3 global_step=5800 optimizer_step=361 loss=1.4605432749
+epoch=3 global_step=5900 optimizer_step=368 loss=1.4312555790
+epoch=3 global_step=6000 optimizer_step=374 loss=1.3502067327
+epoch=3 global_step=6100 optimizer_step=380 loss=1.4576175213
+epoch=3 global_step=6200 optimizer_step=386 loss=1.3821908236
+epoch=3 global_step=6300 optimizer_step=393 loss=1.3928204775
+epoch=3 global_step=6400 optimizer_step=399 loss=1.3881136179
+epoch=3 global_step=6500 optimizer_step=405 loss=1.4001358747
+epoch=3 global_step=6600 optimizer_step=411 loss=1.4551064968
+epoch=3 global_step=6700 optimizer_step=418 loss=1.3845092058
+epoch=3 global_step=6800 optimizer_step=424 loss=1.3578702211
+epoch=3 global_step=6900 optimizer_step=430 loss=1.4272110462
+epoch=3 global_step=7000 optimizer_step=436 loss=1.3858338594
+epoch=3 global_step=7100 optimizer_step=443 loss=1.3530687094
+epoch=3 global_step=7200 optimizer_step=449 loss=1.3435549736
+epoch=3 global_step=7300 optimizer_step=455 loss=1.4043143988
+epoch=3 global_step=7400 optimizer_step=461 loss=1.3953660727
+epoch=3 global_step=7500 optimizer_step=468 loss=1.3620573282
+epoch=4 global_step=7600 optimizer_step=474 loss=1.3935345411
+epoch=4 global_step=7700 optimizer_step=480 loss=1.4139115810
+epoch=4 global_step=7800 optimizer_step=486 loss=1.3389947414
+epoch=4 global_step=7900 optimizer_step=492 loss=1.3918172121
+epoch=4 global_step=8000 optimizer_step=499 loss=1.3609322309
+epoch=4 global_step=8100 optimizer_step=505 loss=1.4061844349
+epoch=4 global_step=8200 optimizer_step=511 loss=1.3393613100
+epoch=4 global_step=8300 optimizer_step=517 loss=1.3928974867
+epoch=4 global_step=8400 optimizer_step=524 loss=1.3271460533
+epoch=4 global_step=8500 optimizer_step=530 loss=1.2875821590
+epoch=4 global_step=8600 optimizer_step=536 loss=1.3289048672
+epoch=4 global_step=8700 optimizer_step=542 loss=1.2611367702
+epoch=4 global_step=8800 optimizer_step=549 loss=1.3173983097
+epoch=4 global_step=8900 optimizer_step=555 loss=1.2802121639
+epoch=4 global_step=9000 optimizer_step=561 loss=1.3014438152
+epoch=4 global_step=9100 optimizer_step=567 loss=1.3053845167
+epoch=4 global_step=9200 optimizer_step=574 loss=1.3083646297
+epoch=4 global_step=9300 optimizer_step=580 loss=1.3026523590
+epoch=5 global_step=9400 optimizer_step=586 loss=1.2748022079
+epoch=5 global_step=9500 optimizer_step=592 loss=1.2720093727
+epoch=5 global_step=9600 optimizer_step=599 loss=1.2576115131
+epoch=5 global_step=9700 optimizer_step=605 loss=1.2540619373
+epoch=5 global_step=9800 optimizer_step=611 loss=1.2503036261
+epoch=5 global_step=9900 optimizer_step=617 loss=1.2791438103
+epoch=5 global_step=10000 optimizer_step=624 loss=1.2408649921
+epoch=5 global_step=10100 optimizer_step=630 loss=1.3279463053
+epoch=5 global_step=10200 optimizer_step=636 loss=1.2726669312
+epoch=5 global_step=10300 optimizer_step=642 loss=1.2991156578
+epoch=5 global_step=10400 optimizer_step=649 loss=1.2505340576
+epoch=5 global_step=10500 optimizer_step=655 loss=1.1945933104
+epoch=5 global_step=10600 optimizer_step=661 loss=1.3188030720
+epoch=5 global_step=10700 optimizer_step=667 loss=1.2800629139
+epoch=5 global_step=10800 optimizer_step=674 loss=1.2652772665
+epoch=5 global_step=10900 optimizer_step=680 loss=1.2236118317
+epoch=5 global_step=11000 optimizer_step=686 loss=1.2195637226
+epoch=5 global_step=11100 optimizer_step=692 loss=1.2912992239
+epoch=5 global_step=11200 optimizer_step=699 loss=1.2282047272
+epoch=6 global_step=11300 optimizer_step=705 loss=1.2542297840
+epoch=6 global_step=11400 optimizer_step=711 loss=1.2346597910
+epoch=6 global_step=11500 optimizer_step=717 loss=1.2334600687
+epoch=6 global_step=11600 optimizer_step=723 loss=1.2842307091
+epoch=6 global_step=11700 optimizer_step=730 loss=1.1844763756
+epoch=6 global_step=11800 optimizer_step=736 loss=1.2523493767
+epoch=6 global_step=11900 optimizer_step=742 loss=1.1639595032
+epoch=6 global_step=12000 optimizer_step=748 loss=1.1894164085
+epoch=6 global_step=12100 optimizer_step=755 loss=1.2072165012
+epoch=6 global_step=12200 optimizer_step=761 loss=1.1584933996
+epoch=6 global_step=12300 optimizer_step=767 loss=1.2422633171
+epoch=6 global_step=12400 optimizer_step=773 loss=1.1490075588
+epoch=6 global_step=12500 optimizer_step=780 loss=1.1903810501
+epoch=6 global_step=12600 optimizer_step=786 loss=1.2166969776
+epoch=6 global_step=12700 optimizer_step=792 loss=1.1963332891
+epoch=6 global_step=12800 optimizer_step=798 loss=1.1964746714
+epoch=6 global_step=12900 optimizer_step=805 loss=1.2591809034
+epoch=6 global_step=13000 optimizer_step=811 loss=1.1972100735
+epoch=6 global_step=13100 optimizer_step=817 loss=1.1826908588
+epoch=7 global_step=13200 optimizer_step=823 loss=1.1766338348
+epoch=7 global_step=13300 optimizer_step=829 loss=1.1584280729
+epoch=7 global_step=13400 optimizer_step=836 loss=1.1913665533
+epoch=7 global_step=13500 optimizer_step=842 loss=1.1882541180
+epoch=7 global_step=13600 optimizer_step=848 loss=1.1557388306
+epoch=7 global_step=13700 optimizer_step=854 loss=1.1235638857
+epoch=7 global_step=13800 optimizer_step=861 loss=1.1839641333
+epoch=7 global_step=13900 optimizer_step=867 loss=1.1647113562
+epoch=7 global_step=14000 optimizer_step=873 loss=1.2438544035
+epoch=7 global_step=14100 optimizer_step=879 loss=1.1640865803
+epoch=7 global_step=14200 optimizer_step=886 loss=1.1870504618
+epoch=7 global_step=14300 optimizer_step=892 loss=1.1519421339
+epoch=7 global_step=14400 optimizer_step=898 loss=1.1744706631
+epoch=7 global_step=14500 optimizer_step=904 loss=1.1462283134
+epoch=7 global_step=14600 optimizer_step=911 loss=1.1813167334
+epoch=7 global_step=14700 optimizer_step=917 loss=1.1782392263
+epoch=7 global_step=14800 optimizer_step=923 loss=1.1728360653
+epoch=7 global_step=14900 optimizer_step=929 loss=1.2018837929
+epoch=7 global_step=15000 optimizer_step=936 loss=1.1150367260
+epoch=8 global_step=15100 optimizer_step=942 loss=1.1753596067
+epoch=8 global_step=15200 optimizer_step=948 loss=1.1770609617
+epoch=8 global_step=15300 optimizer_step=954 loss=1.1861521006
+epoch=8 global_step=15400 optimizer_step=960 loss=1.1599519253
+epoch=8 global_step=15500 optimizer_step=967 loss=1.1394795179
+epoch=8 global_step=15600 optimizer_step=973 loss=1.1791404486
+epoch=8 global_step=15700 optimizer_step=979 loss=1.1048771143
+epoch=8 global_step=15800 optimizer_step=985 loss=1.1294406652
+epoch=8 global_step=15900 optimizer_step=992 loss=1.1038743258
+epoch=8 global_step=16000 optimizer_step=998 loss=1.1219477654
+epoch=8 global_step=16100 optimizer_step=1004 loss=1.1075527668
+epoch=8 global_step=16200 optimizer_step=1010 loss=1.1164005995
+epoch=8 global_step=16300 optimizer_step=1017 loss=1.1328935623
+epoch=8 global_step=16400 optimizer_step=1023 loss=1.1978664398
+epoch=8 global_step=16500 optimizer_step=1029 loss=1.1623390913
+epoch=8 global_step=16600 optimizer_step=1035 loss=1.1286399364
+epoch=8 global_step=16700 optimizer_step=1042 loss=1.1228419542
+epoch=8 global_step=16800 optimizer_step=1048 loss=1.1309365034
+epoch=9 global_step=16900 optimizer_step=1054 loss=1.1923186779
+epoch=9 global_step=17000 optimizer_step=1060 loss=1.1374170780
+epoch=9 global_step=17100 optimizer_step=1067 loss=1.1110630035
+epoch=9 global_step=17200 optimizer_step=1073 loss=1.1366587877
+epoch=9 global_step=17300 optimizer_step=1079 loss=1.1502659321
+epoch=9 global_step=17400 optimizer_step=1085 loss=1.1444725990
+epoch=9 global_step=17500 optimizer_step=1092 loss=1.1149526834
+epoch=9 global_step=17600 optimizer_step=1098 loss=1.1393855810
+epoch=9 global_step=17700 optimizer_step=1104 loss=1.0747587681
+epoch=9 global_step=17800 optimizer_step=1110 loss=1.2174261808
+epoch=9 global_step=17900 optimizer_step=1117 loss=1.1408920288
+epoch=9 global_step=18000 optimizer_step=1123 loss=1.1306611300
+epoch=9 global_step=18100 optimizer_step=1129 loss=1.1112066507
+epoch=9 global_step=18200 optimizer_step=1135 loss=1.1340869665
+epoch=9 global_step=18300 optimizer_step=1142 loss=1.1117720604
+epoch=9 global_step=18400 optimizer_step=1148 loss=1.1233191490
+epoch=9 global_step=18500 optimizer_step=1154 loss=1.1748867035
+epoch=9 global_step=18600 optimizer_step=1160 loss=1.1060826778
+epoch=9 global_step=18700 optimizer_step=1167 loss=1.1303336620
+epoch=10 global_step=18800 optimizer_step=1173 loss=1.1331672668
+epoch=10 global_step=18900 optimizer_step=1179 loss=1.1120133400
+epoch=10 global_step=19000 optimizer_step=1185 loss=1.0921238661
+epoch=10 global_step=19100 optimizer_step=1191 loss=1.1474208832
+epoch=10 global_step=19200 optimizer_step=1198 loss=1.1801259518
+epoch=10 global_step=19300 optimizer_step=1204 loss=1.0749396086
+epoch=10 global_step=19400 optimizer_step=1210 loss=1.1091520786
+epoch=10 global_step=19500 optimizer_step=1216 loss=1.0877908468
+epoch=10 global_step=19600 optimizer_step=1223 loss=1.0849142075
+epoch=10 global_step=19700 optimizer_step=1229 loss=1.1071676016
+epoch=10 global_step=19800 optimizer_step=1235 loss=1.0699013472
+epoch=10 global_step=19900 optimizer_step=1241 loss=1.1382901669
+epoch=10 global_step=20000 optimizer_step=1248 loss=1.0821399689
+epoch=10 global_step=20100 optimizer_step=1254 loss=1.0577888489
+epoch=10 global_step=20200 optimizer_step=1260 loss=1.1225908995
+epoch=10 global_step=20300 optimizer_step=1266 loss=1.0864553452
+epoch=10 global_step=20400 optimizer_step=1273 loss=1.0812349319
+epoch=10 global_step=20500 optimizer_step=1279 loss=1.0915205479
+epoch=10 global_step=20600 optimizer_step=1285 loss=1.1540257931
+epoch=11 global_step=20700 optimizer_step=1291 loss=1.0546641350
+epoch=11 global_step=20800 optimizer_step=1297 loss=1.0720232725
+epoch=11 global_step=20900 optimizer_step=1304 loss=1.0815181732
+epoch=11 global_step=21000 optimizer_step=1310 loss=1.1323018074
+epoch=11 global_step=21100 optimizer_step=1316 loss=1.0693240166
+epoch=11 global_step=21200 optimizer_step=1322 loss=1.0532209873
+epoch=11 global_step=21300 optimizer_step=1329 loss=1.0408358574
+epoch=11 global_step=21400 optimizer_step=1335 loss=1.0846587420
+epoch=11 global_step=21500 optimizer_step=1341 loss=1.0737553835
+epoch=11 global_step=21600 optimizer_step=1347 loss=1.0870618820
+epoch=11 global_step=21700 optimizer_step=1354 loss=1.0678054094
+epoch=11 global_step=21800 optimizer_step=1360 loss=1.0347111225
+epoch=11 global_step=21900 optimizer_step=1366 loss=1.0453056097
+epoch=11 global_step=22000 optimizer_step=1372 loss=1.0897388458
+epoch=11 global_step=22100 optimizer_step=1379 loss=1.1514784098
+epoch=11 global_step=22200 optimizer_step=1385 loss=1.0781635046
+epoch=11 global_step=22300 optimizer_step=1391 loss=1.1274259090
+epoch=11 global_step=22400 optimizer_step=1397 loss=1.0955965519
+epoch=11 global_step=22500 optimizer_step=1404 loss=1.0160986185
+epoch=12 global_step=22600 optimizer_step=1410 loss=0.9995673299
+epoch=12 global_step=22700 optimizer_step=1416 loss=1.0190529823
+epoch=12 global_step=22800 optimizer_step=1422 loss=1.0622847080
+epoch=12 global_step=22900 optimizer_step=1428 loss=1.0493798256
+epoch=12 global_step=23000 optimizer_step=1435 loss=1.0612323284
+epoch=12 global_step=23100 optimizer_step=1441 loss=1.0908408165
+epoch=12 global_step=23200 optimizer_step=1447 loss=1.0020720959
+epoch=12 global_step=23300 optimizer_step=1453 loss=1.0688211918
+epoch=12 global_step=23400 optimizer_step=1460 loss=1.0861740112
+epoch=12 global_step=23500 optimizer_step=1466 loss=1.1090929508
+epoch=12 global_step=23600 optimizer_step=1472 loss=1.0873198509
+epoch=12 global_step=23700 optimizer_step=1478 loss=1.0886340141
+epoch=12 global_step=23800 optimizer_step=1485 loss=1.0512799025
+epoch=12 global_step=23900 optimizer_step=1491 loss=0.9775702357
+epoch=12 global_step=24000 optimizer_step=1497 loss=1.0613026619
+epoch=12 global_step=24100 optimizer_step=1503 loss=1.0493617058
+epoch=12 global_step=24200 optimizer_step=1510 loss=1.1572235823
+epoch=12 global_step=24300 optimizer_step=1516 loss=1.0219266415
+epoch=13 global_step=24400 optimizer_step=1522 loss=1.0526365042
+epoch=13 global_step=24500 optimizer_step=1528 loss=1.0169779062
+epoch=13 global_step=24600 optimizer_step=1535 loss=1.0194381475
+epoch=13 global_step=24700 optimizer_step=1541 loss=1.0518094301
+epoch=13 global_step=24800 optimizer_step=1547 loss=1.0707962513
+epoch=13 global_step=24900 optimizer_step=1553 loss=1.0235271454
+epoch=13 global_step=25000 optimizer_step=1560 loss=1.0677742958
+epoch=13 global_step=25100 optimizer_step=1566 loss=1.0691384077
+epoch=13 global_step=25200 optimizer_step=1572 loss=1.0067445040
+epoch=13 global_step=25300 optimizer_step=1578 loss=1.0540893078
+epoch=13 global_step=25400 optimizer_step=1585 loss=1.0311323404
+epoch=13 global_step=25500 optimizer_step=1591 loss=1.0564373732
+epoch=13 global_step=25600 optimizer_step=1597 loss=1.1479471922
+epoch=13 global_step=25700 optimizer_step=1603 loss=0.9929249883
+epoch=13 global_step=25800 optimizer_step=1610 loss=1.0696063042
+epoch=13 global_step=25900 optimizer_step=1616 loss=1.0555770397
+epoch=13 global_step=26000 optimizer_step=1622 loss=1.0865052938
+epoch=13 global_step=26100 optimizer_step=1628 loss=1.0020205975
+epoch=13 global_step=26200 optimizer_step=1635 loss=1.0150972605
+epoch=14 global_step=26300 optimizer_step=1641 loss=1.1214226484
+epoch=14 global_step=26400 optimizer_step=1647 loss=1.0504353046
+epoch=14 global_step=26500 optimizer_step=1653 loss=0.9970446229
+epoch=14 global_step=26600 optimizer_step=1659 loss=1.0572619438
+epoch=14 global_step=26700 optimizer_step=1666 loss=1.0367437601
+epoch=14 global_step=26800 optimizer_step=1672 loss=1.0528297424
+epoch=14 global_step=26900 optimizer_step=1678 loss=0.9394198060
+epoch=14 global_step=27000 optimizer_step=1684 loss=1.0272345543
+epoch=14 global_step=27100 optimizer_step=1691 loss=1.0158746243
+epoch=14 global_step=27200 optimizer_step=1697 loss=1.0190368891
+epoch=14 global_step=27300 optimizer_step=1703 loss=1.1217275858
+epoch=14 global_step=27400 optimizer_step=1709 loss=1.0739328861
+epoch=14 global_step=27500 optimizer_step=1716 loss=1.0125224590
+epoch=14 global_step=27600 optimizer_step=1722 loss=1.0331842899
+epoch=14 global_step=27700 optimizer_step=1728 loss=1.0070307255
+epoch=14 global_step=27800 optimizer_step=1734 loss=1.0299409628
+epoch=14 global_step=27900 optimizer_step=1741 loss=1.0568556786
+epoch=14 global_step=28000 optimizer_step=1747 loss=1.0081789494
+epoch=14 global_step=28100 optimizer_step=1753 loss=0.9812691808
+epoch=15 global_step=28200 optimizer_step=1759 loss=1.0139238834
+epoch=15 global_step=28300 optimizer_step=1765 loss=1.0415730476
+epoch=15 global_step=28400 optimizer_step=1772 loss=1.0350427628
+epoch=15 global_step=28500 optimizer_step=1778 loss=1.0088034868
+epoch=15 global_step=28600 optimizer_step=1784 loss=1.0223383904
+epoch=15 global_step=28700 optimizer_step=1790 loss=0.9988454580
+epoch=15 global_step=28800 optimizer_step=1797 loss=0.9836750627
+epoch=15 global_step=28900 optimizer_step=1803 loss=1.0617191792
+epoch=15 global_step=29000 optimizer_step=1809 loss=1.0052067041
+epoch=15 global_step=29100 optimizer_step=1815 loss=1.0165585279
+epoch=15 global_step=29200 optimizer_step=1822 loss=0.9680172801
+epoch=15 global_step=29300 optimizer_step=1828 loss=0.9979470372
+epoch=15 global_step=29400 optimizer_step=1834 loss=1.0205397606
+epoch=15 global_step=29500 optimizer_step=1840 loss=1.0423145294
+epoch=15 global_step=29600 optimizer_step=1847 loss=1.0312378407
+epoch=15 global_step=29700 optimizer_step=1853 loss=0.9797540903
+epoch=15 global_step=29800 optimizer_step=1859 loss=0.9774625301
+epoch=15 global_step=29900 optimizer_step=1865 loss=0.9693509340
+epoch=15 global_step=30000 optimizer_step=1872 loss=0.9987518191
+epoch=16 global_step=30100 optimizer_step=1878 loss=0.9946843386
+epoch=16 global_step=30200 optimizer_step=1884 loss=0.9664356709
+epoch=16 global_step=30300 optimizer_step=1890 loss=0.9686496854
+epoch=16 global_step=30400 optimizer_step=1896 loss=1.0121268034
+epoch=16 global_step=30500 optimizer_step=1903 loss=0.9790974259
+epoch=16 global_step=30600 optimizer_step=1909 loss=0.9773679972
+epoch=16 global_step=30700 optimizer_step=1915 loss=0.9834152460
+epoch=16 global_step=30800 optimizer_step=1921 loss=0.9650681615
+epoch=16 global_step=30900 optimizer_step=1928 loss=0.9872033596
+epoch=16 global_step=31000 optimizer_step=1934 loss=0.9843855500
+epoch=16 global_step=31100 optimizer_step=1940 loss=1.0217592716
+epoch=16 global_step=31200 optimizer_step=1946 loss=0.9632706642
+epoch=16 global_step=31300 optimizer_step=1953 loss=0.9589420557
+epoch=16 global_step=31400 optimizer_step=1959 loss=1.0082035065
+epoch=16 global_step=31500 optimizer_step=1965 loss=0.9504637718
+epoch=16 global_step=31600 optimizer_step=1971 loss=0.9335161448
+epoch=16 global_step=31700 optimizer_step=1978 loss=1.0115956068
+epoch=16 global_step=31800 optimizer_step=1984 loss=0.9916386604
+epoch=17 global_step=31900 optimizer_step=1990 loss=0.9706923962
+epoch=17 global_step=32000 optimizer_step=1996 loss=0.9643757939
+epoch=17 global_step=32100 optimizer_step=2003 loss=0.9478634596
+epoch=17 global_step=32200 optimizer_step=2009 loss=1.0056527853
+epoch=17 global_step=32300 optimizer_step=2015 loss=0.9869378209
+epoch=17 global_step=32400 optimizer_step=2021 loss=0.9422252178
+epoch=17 global_step=32500 optimizer_step=2028 loss=0.9672117829
+epoch=17 global_step=32600 optimizer_step=2034 loss=0.9810509682
+epoch=17 global_step=32700 optimizer_step=2040 loss=0.9930518270
+epoch=17 global_step=32800 optimizer_step=2046 loss=0.9910761118
+epoch=17 global_step=32900 optimizer_step=2053 loss=0.9281983972
+epoch=17 global_step=33000 optimizer_step=2059 loss=0.9772264361
+epoch=17 global_step=33100 optimizer_step=2065 loss=0.9629877806
+epoch=17 global_step=33200 optimizer_step=2071 loss=0.9728618264
+epoch=17 global_step=33300 optimizer_step=2078 loss=0.9579383731
+epoch=17 global_step=33400 optimizer_step=2084 loss=0.9836122394
+epoch=17 global_step=33500 optimizer_step=2090 loss=0.9768933058
+epoch=17 global_step=33600 optimizer_step=2096 loss=0.9953776002
+epoch=17 global_step=33700 optimizer_step=2103 loss=0.9237729907
+epoch=18 global_step=33800 optimizer_step=2109 loss=0.9889909625
+epoch=18 global_step=33900 optimizer_step=2115 loss=0.9803759456
+epoch=18 global_step=34000 optimizer_step=2121 loss=1.0077112913
+epoch=18 global_step=34100 optimizer_step=2127 loss=0.9454981089
+epoch=18 global_step=34200 optimizer_step=2134 loss=0.9688407779
+epoch=18 global_step=34300 optimizer_step=2140 loss=0.9763611555
+epoch=18 global_step=34400 optimizer_step=2146 loss=0.9799119234
+epoch=18 global_step=34500 optimizer_step=2152 loss=0.9221845269
+epoch=18 global_step=34600 optimizer_step=2159 loss=0.9674979448
+epoch=18 global_step=34700 optimizer_step=2165 loss=0.9167769551
+epoch=18 global_step=34800 optimizer_step=2171 loss=0.9421973228
+epoch=18 global_step=34900 optimizer_step=2177 loss=0.9502854943
+epoch=18 global_step=35000 optimizer_step=2184 loss=0.9552825093
+epoch=18 global_step=35100 optimizer_step=2190 loss=0.9516187906
+epoch=18 global_step=35200 optimizer_step=2196 loss=1.0120521784
+epoch=18 global_step=35300 optimizer_step=2202 loss=0.9260447025
+epoch=18 global_step=35400 optimizer_step=2209 loss=0.9488614202
+epoch=18 global_step=35500 optimizer_step=2215 loss=0.9439768791
+epoch=18 global_step=35600 optimizer_step=2221 loss=0.9762747884
+epoch=19 global_step=35700 optimizer_step=2227 loss=0.9873654842
+epoch=19 global_step=35800 optimizer_step=2233 loss=0.9932043552
+epoch=19 global_step=35900 optimizer_step=2240 loss=0.9861009121
+epoch=19 global_step=36000 optimizer_step=2246 loss=0.9882121086
+epoch=19 global_step=36100 optimizer_step=2252 loss=0.9479538202
+epoch=19 global_step=36200 optimizer_step=2258 loss=0.9752264023
+epoch=19 global_step=36300 optimizer_step=2265 loss=1.0133050680
+epoch=19 global_step=36400 optimizer_step=2271 loss=0.9196277261
+epoch=19 global_step=36500 optimizer_step=2277 loss=0.9979407787
+epoch=19 global_step=36600 optimizer_step=2283 loss=0.9545599222
+epoch=19 global_step=36700 optimizer_step=2290 loss=0.9229099154
+epoch=19 global_step=36800 optimizer_step=2296 loss=0.9422724843
+epoch=19 global_step=36900 optimizer_step=2302 loss=0.9293218851
+epoch=19 global_step=37000 optimizer_step=2308 loss=0.9575501084
+epoch=19 global_step=37100 optimizer_step=2315 loss=0.9449048638
+epoch=19 global_step=37200 optimizer_step=2321 loss=1.0184578896
+epoch=19 global_step=37300 optimizer_step=2327 loss=0.9043714404
+epoch=19 global_step=37400 optimizer_step=2333 loss=0.9538159370
+epoch=19 global_step=37500 optimizer_step=2340 loss=0.9813507795