upload

.gitattributes

@@ -51,3 +51,4 @@ llmstream_results/qwen3_17b_base_streamline_slimpajama_prune4_start11/tokenizer.
 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_prune10_start11/tokenizer.json filter=lfs diff=lfs merge=lfs -text

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune10_start11/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_prune10_start11/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_prune10_start11/config.json

@@ -0,0 +1,49 @@
+{
+  "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"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 18,
+  "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_prune10_start11/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_prune10_start11/lightweight_checkpoint_epoch_10/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b8ea3666fdb3ae1b8ce678327f990549126134473aec5a96047481a7067975d
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune10_start11/lightweight_checkpoint_epoch_12/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c08e474bb804413706368ecf56a0842f14717206c3d8d24c870e5d8c2848aa0
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune10_start11/lightweight_checkpoint_epoch_14/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61f54035ff21cc1816c8d2feb0538f7a85e0870fcdd552485f58c966e8d4066a
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune10_start11/lightweight_checkpoint_epoch_16/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c14174e31a09621e46cceacf805f70b82bbb85fa395a882842cc8e1954f29f0c
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune10_start11/lightweight_checkpoint_epoch_18/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22597ba6bb46f37dae2d72bbae2ca30f2f3cea99b559d1c9814b59a7479f81d5
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune10_start11/lightweight_checkpoint_epoch_2/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2160d88f9f4bd0d0ca2cfbbc7a4de33ebce35d4a2b46d15ed13581f3c519fed
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune10_start11/lightweight_checkpoint_epoch_20/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5064d0a019b235e0f0e3b8b9f0e5dabbca5a382774535807e0310d02897a183e
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune10_start11/lightweight_checkpoint_epoch_4/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9369db61c4801a338265e94f637ebc3f989f4ec6dc97f0cd2dfcd6b0bd577597
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune10_start11/lightweight_checkpoint_epoch_6/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f1a9448a17054d0a0b3fde27b40d75c46e00b100b3386a6811a0c00296b5e30
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune10_start11/lightweight_checkpoint_epoch_8/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79703ba5d1f2383475cc86de7e0551394595406787b5108968f22191456629d1
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune10_start11/lightweight_checkpoint_final/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5064d0a019b235e0f0e3b8b9f0e5dabbca5a382774535807e0310d02897a183e
+size 932236853

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune10_start11/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_prune10_start11/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccea24db0022aea4aa4e070d13596591fc49404bbcbda0dd34b170a2733d189d
+size 4602446584

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune10_start11/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5be8567a86b9f8fdf251358a5757baf1e45239e4ba2ed2bb04d81d824a7031c5
+size 1089994880

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune10_start11/model.safetensors.index.json

@@ -0,0 +1,227 @@
+{
+  "metadata": {
+    "total_parameters": 5285038592,
+    "total_size": 10570077184
+  },
+  "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.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.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-00002-of-00003.safetensors"
+  }
+}

llmstream_results/qwen25_7b_base_streamline_slimpajama_prune10_start11/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_prune10_start11 --dataset slimpajama --dataset_split train --layer_intervals 10 --best_layer 11 --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_prune10_start11/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_prune10_start11/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_prune10_start11/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_prune10_start11/train_loss.txt

@@ -0,0 +1,376 @@
+# Train loss logged every 100 global steps
+epoch=0 global_step=100 optimizer_step=6 loss=4.2064185143
+epoch=0 global_step=200 optimizer_step=12 loss=4.3834743500
+epoch=0 global_step=300 optimizer_step=18 loss=4.4329085350
+epoch=0 global_step=400 optimizer_step=24 loss=4.6018309593
+epoch=0 global_step=500 optimizer_step=31 loss=4.1773409843
+epoch=0 global_step=600 optimizer_step=37 loss=4.3640112877
+epoch=0 global_step=700 optimizer_step=43 loss=4.2505373955
+epoch=0 global_step=800 optimizer_step=49 loss=4.1636362076
+epoch=0 global_step=900 optimizer_step=56 loss=4.3956465721
+epoch=0 global_step=1000 optimizer_step=62 loss=4.2384166718
+epoch=0 global_step=1100 optimizer_step=68 loss=4.3135581017
+epoch=0 global_step=1200 optimizer_step=74 loss=4.3415369987
+epoch=0 global_step=1300 optimizer_step=81 loss=4.1753139496
+epoch=0 global_step=1400 optimizer_step=87 loss=4.3210592270
+epoch=0 global_step=1500 optimizer_step=93 loss=4.1443238258
+epoch=0 global_step=1600 optimizer_step=99 loss=3.9903964996
+epoch=0 global_step=1700 optimizer_step=106 loss=3.8895740509
+epoch=0 global_step=1800 optimizer_step=112 loss=3.9230337143
+epoch=1 global_step=1900 optimizer_step=118 loss=3.9657447338
+epoch=1 global_step=2000 optimizer_step=124 loss=3.8345787525
+epoch=1 global_step=2100 optimizer_step=131 loss=3.7174422741
+epoch=1 global_step=2200 optimizer_step=137 loss=3.7261970043
+epoch=1 global_step=2300 optimizer_step=143 loss=3.6614289284
+epoch=1 global_step=2400 optimizer_step=149 loss=3.7094693184
+epoch=1 global_step=2500 optimizer_step=156 loss=3.3921208382
+epoch=1 global_step=2600 optimizer_step=162 loss=3.5602648258
+epoch=1 global_step=2700 optimizer_step=168 loss=3.4457728863
+epoch=1 global_step=2800 optimizer_step=174 loss=3.3466539383
+epoch=1 global_step=2900 optimizer_step=181 loss=3.2985615730
+epoch=1 global_step=3000 optimizer_step=187 loss=3.2482392788
+epoch=1 global_step=3100 optimizer_step=193 loss=3.2604060173
+epoch=1 global_step=3200 optimizer_step=199 loss=3.1869840622
+epoch=1 global_step=3300 optimizer_step=206 loss=3.1626188755
+epoch=1 global_step=3400 optimizer_step=212 loss=3.2723600864
+epoch=1 global_step=3500 optimizer_step=218 loss=3.0695650578
+epoch=1 global_step=3600 optimizer_step=224 loss=3.1810445786
+epoch=1 global_step=3700 optimizer_step=231 loss=3.1576516628
+epoch=2 global_step=3800 optimizer_step=237 loss=3.1682047844
+epoch=2 global_step=3900 optimizer_step=243 loss=3.0371081829
+epoch=2 global_step=4000 optimizer_step=249 loss=3.0111417770
+epoch=2 global_step=4100 optimizer_step=255 loss=2.9646418095
+epoch=2 global_step=4200 optimizer_step=262 loss=3.0579659939
+epoch=2 global_step=4300 optimizer_step=268 loss=3.0847680569
+epoch=2 global_step=4400 optimizer_step=274 loss=3.0288255215
+epoch=2 global_step=4500 optimizer_step=280 loss=2.9489703178
+epoch=2 global_step=4600 optimizer_step=287 loss=3.0951719284
+epoch=2 global_step=4700 optimizer_step=293 loss=2.9574110508
+epoch=2 global_step=4800 optimizer_step=299 loss=2.9654834270
+epoch=2 global_step=4900 optimizer_step=305 loss=2.8531711102
+epoch=2 global_step=5000 optimizer_step=312 loss=3.0117876530
+epoch=2 global_step=5100 optimizer_step=318 loss=2.9510738850
+epoch=2 global_step=5200 optimizer_step=324 loss=2.7762742043
+epoch=2 global_step=5300 optimizer_step=330 loss=2.9029281139
+epoch=2 global_step=5400 optimizer_step=337 loss=2.7632615566
+epoch=2 global_step=5500 optimizer_step=343 loss=2.8750278950
+epoch=2 global_step=5600 optimizer_step=349 loss=2.7498414516
+epoch=3 global_step=5700 optimizer_step=355 loss=2.8321955204
+epoch=3 global_step=5800 optimizer_step=361 loss=2.7935111523
+epoch=3 global_step=5900 optimizer_step=368 loss=2.6816227436
+epoch=3 global_step=6000 optimizer_step=374 loss=2.8096659184
+epoch=3 global_step=6100 optimizer_step=380 loss=2.8450875282
+epoch=3 global_step=6200 optimizer_step=386 loss=2.7680299282
+epoch=3 global_step=6300 optimizer_step=393 loss=2.6644432545
+epoch=3 global_step=6400 optimizer_step=399 loss=2.6151289940
+epoch=3 global_step=6500 optimizer_step=405 loss=2.7646567822
+epoch=3 global_step=6600 optimizer_step=411 loss=2.6138262749
+epoch=3 global_step=6700 optimizer_step=418 loss=2.6511306763
+epoch=3 global_step=6800 optimizer_step=424 loss=2.6844241619
+epoch=3 global_step=6900 optimizer_step=430 loss=2.5942089558
+epoch=3 global_step=7000 optimizer_step=436 loss=2.6846020222
+epoch=3 global_step=7100 optimizer_step=443 loss=2.5698223114
+epoch=3 global_step=7200 optimizer_step=449 loss=2.5340552330
+epoch=3 global_step=7300 optimizer_step=455 loss=2.5656771660
+epoch=3 global_step=7400 optimizer_step=461 loss=2.5926465988
+epoch=3 global_step=7500 optimizer_step=468 loss=2.6569614410
+epoch=4 global_step=7600 optimizer_step=474 loss=2.6181278229
+epoch=4 global_step=7700 optimizer_step=480 loss=2.5686168671
+epoch=4 global_step=7800 optimizer_step=486 loss=2.6285114288
+epoch=4 global_step=7900 optimizer_step=492 loss=2.6996042728
+epoch=4 global_step=8000 optimizer_step=499 loss=2.5703082085
+epoch=4 global_step=8100 optimizer_step=505 loss=2.5925936699
+epoch=4 global_step=8200 optimizer_step=511 loss=2.7275357246
+epoch=4 global_step=8300 optimizer_step=517 loss=2.5800924301
+epoch=4 global_step=8400 optimizer_step=524 loss=2.5587382317
+epoch=4 global_step=8500 optimizer_step=530 loss=2.5844624043
+epoch=4 global_step=8600 optimizer_step=536 loss=2.4965274334
+epoch=4 global_step=8700 optimizer_step=542 loss=2.6475269794
+epoch=4 global_step=8800 optimizer_step=549 loss=2.6127610207
+epoch=4 global_step=8900 optimizer_step=555 loss=2.5892829895
+epoch=4 global_step=9000 optimizer_step=561 loss=2.6797051430
+epoch=4 global_step=9100 optimizer_step=567 loss=2.4794769287
+epoch=4 global_step=9200 optimizer_step=574 loss=2.5396583080
+epoch=4 global_step=9300 optimizer_step=580 loss=2.4299840927
+epoch=5 global_step=9400 optimizer_step=586 loss=2.5009660721
+epoch=5 global_step=9500 optimizer_step=592 loss=2.5086660385
+epoch=5 global_step=9600 optimizer_step=599 loss=2.5132491589
+epoch=5 global_step=9700 optimizer_step=605 loss=2.4074134827
+epoch=5 global_step=9800 optimizer_step=611 loss=2.4442057610
+epoch=5 global_step=9900 optimizer_step=617 loss=2.3317370415
+epoch=5 global_step=10000 optimizer_step=624 loss=2.4170231819
+epoch=5 global_step=10100 optimizer_step=630 loss=2.5932440758
+epoch=5 global_step=10200 optimizer_step=636 loss=2.4321491718
+epoch=5 global_step=10300 optimizer_step=642 loss=2.3944976330
+epoch=5 global_step=10400 optimizer_step=649 loss=2.4727120399
+epoch=5 global_step=10500 optimizer_step=655 loss=2.3586976528
+epoch=5 global_step=10600 optimizer_step=661 loss=2.4479856491
+epoch=5 global_step=10700 optimizer_step=667 loss=2.3848407269
+epoch=5 global_step=10800 optimizer_step=674 loss=2.4093103409
+epoch=5 global_step=10900 optimizer_step=680 loss=2.3804299831
+epoch=5 global_step=11000 optimizer_step=686 loss=2.3680448532
+epoch=5 global_step=11100 optimizer_step=692 loss=2.3709449768
+epoch=5 global_step=11200 optimizer_step=699 loss=2.2601552010
+epoch=6 global_step=11300 optimizer_step=705 loss=2.2857460976
+epoch=6 global_step=11400 optimizer_step=711 loss=2.3774695396
+epoch=6 global_step=11500 optimizer_step=717 loss=2.3599174023
+epoch=6 global_step=11600 optimizer_step=723 loss=2.3892858028
+epoch=6 global_step=11700 optimizer_step=730 loss=2.3476595879
+epoch=6 global_step=11800 optimizer_step=736 loss=2.2420120239
+epoch=6 global_step=11900 optimizer_step=742 loss=2.3708851337
+epoch=6 global_step=12000 optimizer_step=748 loss=2.2299220562
+epoch=6 global_step=12100 optimizer_step=755 loss=2.3888206482
+epoch=6 global_step=12200 optimizer_step=761 loss=2.3593301773
+epoch=6 global_step=12300 optimizer_step=767 loss=2.2660098076
+epoch=6 global_step=12400 optimizer_step=773 loss=2.3233299255
+epoch=6 global_step=12500 optimizer_step=780 loss=2.2892661095
+epoch=6 global_step=12600 optimizer_step=786 loss=2.3545327187
+epoch=6 global_step=12700 optimizer_step=792 loss=2.3232827187
+epoch=6 global_step=12800 optimizer_step=798 loss=2.2995200157
+epoch=6 global_step=12900 optimizer_step=805 loss=2.3280320168
+epoch=6 global_step=13000 optimizer_step=811 loss=2.2878425121
+epoch=6 global_step=13100 optimizer_step=817 loss=2.3553206921
+epoch=7 global_step=13200 optimizer_step=823 loss=2.2445640564
+epoch=7 global_step=13300 optimizer_step=829 loss=2.3537468910
+epoch=7 global_step=13400 optimizer_step=836 loss=2.2628211975
+epoch=7 global_step=13500 optimizer_step=842 loss=2.3023746014
+epoch=7 global_step=13600 optimizer_step=848 loss=2.3351521492
+epoch=7 global_step=13700 optimizer_step=854 loss=2.3170485497
+epoch=7 global_step=13800 optimizer_step=861 loss=2.2292556763
+epoch=7 global_step=13900 optimizer_step=867 loss=2.2210650444
+epoch=7 global_step=14000 optimizer_step=873 loss=2.2788352966
+epoch=7 global_step=14100 optimizer_step=879 loss=2.3585457802
+epoch=7 global_step=14200 optimizer_step=886 loss=2.2154512405
+epoch=7 global_step=14300 optimizer_step=892 loss=2.2092168331
+epoch=7 global_step=14400 optimizer_step=898 loss=2.2144069672
+epoch=7 global_step=14500 optimizer_step=904 loss=2.3024621010
+epoch=7 global_step=14600 optimizer_step=911 loss=2.1608607769
+epoch=7 global_step=14700 optimizer_step=917 loss=2.3100478649
+epoch=7 global_step=14800 optimizer_step=923 loss=2.2317757607
+epoch=7 global_step=14900 optimizer_step=929 loss=2.2253789902
+epoch=7 global_step=15000 optimizer_step=936 loss=2.2347288132
+epoch=8 global_step=15100 optimizer_step=942 loss=2.2768716812
+epoch=8 global_step=15200 optimizer_step=948 loss=2.1574850082
+epoch=8 global_step=15300 optimizer_step=954 loss=2.2107594013
+epoch=8 global_step=15400 optimizer_step=960 loss=2.2412412167
+epoch=8 global_step=15500 optimizer_step=967 loss=2.2133150101
+epoch=8 global_step=15600 optimizer_step=973 loss=2.2716112137
+epoch=8 global_step=15700 optimizer_step=979 loss=2.2257018089
+epoch=8 global_step=15800 optimizer_step=985 loss=2.1897492409
+epoch=8 global_step=15900 optimizer_step=992 loss=2.1891024113
+epoch=8 global_step=16000 optimizer_step=998 loss=2.1907215118
+epoch=8 global_step=16100 optimizer_step=1004 loss=2.1437687874
+epoch=8 global_step=16200 optimizer_step=1010 loss=2.1803727150
+epoch=8 global_step=16300 optimizer_step=1017 loss=2.1683812141
+epoch=8 global_step=16400 optimizer_step=1023 loss=2.1828007698
+epoch=8 global_step=16500 optimizer_step=1029 loss=2.1553106308
+epoch=8 global_step=16600 optimizer_step=1035 loss=2.1967990398
+epoch=8 global_step=16700 optimizer_step=1042 loss=2.1436507702
+epoch=8 global_step=16800 optimizer_step=1048 loss=2.1677906513
+epoch=9 global_step=16900 optimizer_step=1054 loss=2.1608178616
+epoch=9 global_step=17000 optimizer_step=1060 loss=2.2230412960
+epoch=9 global_step=17100 optimizer_step=1067 loss=2.1993501186
+epoch=9 global_step=17200 optimizer_step=1073 loss=2.1875653267
+epoch=9 global_step=17300 optimizer_step=1079 loss=2.1818943024
+epoch=9 global_step=17400 optimizer_step=1085 loss=2.1738281250
+epoch=9 global_step=17500 optimizer_step=1092 loss=2.1786448956
+epoch=9 global_step=17600 optimizer_step=1098 loss=2.1104171276
+epoch=9 global_step=17700 optimizer_step=1104 loss=2.0738949776
+epoch=9 global_step=17800 optimizer_step=1110 loss=2.2347140312
+epoch=9 global_step=17900 optimizer_step=1117 loss=2.1640794277
+epoch=9 global_step=18000 optimizer_step=1123 loss=2.1826155186
+epoch=9 global_step=18100 optimizer_step=1129 loss=2.1211254597
+epoch=9 global_step=18200 optimizer_step=1135 loss=2.1714320183
+epoch=9 global_step=18300 optimizer_step=1142 loss=2.1673102379
+epoch=9 global_step=18400 optimizer_step=1148 loss=2.2552330494
+epoch=9 global_step=18500 optimizer_step=1154 loss=2.1516752243
+epoch=9 global_step=18600 optimizer_step=1160 loss=2.1757996082
+epoch=9 global_step=18700 optimizer_step=1167 loss=2.0436515808
+epoch=10 global_step=18800 optimizer_step=1173 loss=2.2151722908
+epoch=10 global_step=18900 optimizer_step=1179 loss=2.1549899578
+epoch=10 global_step=19000 optimizer_step=1185 loss=2.2874767780
+epoch=10 global_step=19100 optimizer_step=1191 loss=2.2144391537
+epoch=10 global_step=19200 optimizer_step=1198 loss=2.0452530384
+epoch=10 global_step=19300 optimizer_step=1204 loss=2.0694708824
+epoch=10 global_step=19400 optimizer_step=1210 loss=2.1431005001
+epoch=10 global_step=19500 optimizer_step=1216 loss=2.0938539505
+epoch=10 global_step=19600 optimizer_step=1223 loss=2.1567149162
+epoch=10 global_step=19700 optimizer_step=1229 loss=2.1130952835
+epoch=10 global_step=19800 optimizer_step=1235 loss=2.1349265575
+epoch=10 global_step=19900 optimizer_step=1241 loss=2.1729128361
+epoch=10 global_step=20000 optimizer_step=1248 loss=2.1838681698
+epoch=10 global_step=20100 optimizer_step=1254 loss=2.1323256493
+epoch=10 global_step=20200 optimizer_step=1260 loss=2.1485557556
+epoch=10 global_step=20300 optimizer_step=1266 loss=2.0586917400
+epoch=10 global_step=20400 optimizer_step=1273 loss=2.0853338242
+epoch=10 global_step=20500 optimizer_step=1279 loss=2.0427157879
+epoch=10 global_step=20600 optimizer_step=1285 loss=2.0353085995
+epoch=11 global_step=20700 optimizer_step=1291 loss=2.0631425381
+epoch=11 global_step=20800 optimizer_step=1297 loss=2.0341682434
+epoch=11 global_step=20900 optimizer_step=1304 loss=2.1220757961
+epoch=11 global_step=21000 optimizer_step=1310 loss=2.0484032631
+epoch=11 global_step=21100 optimizer_step=1316 loss=2.0140872002
+epoch=11 global_step=21200 optimizer_step=1322 loss=2.0555236340
+epoch=11 global_step=21300 optimizer_step=1329 loss=2.0508761406
+epoch=11 global_step=21400 optimizer_step=1335 loss=2.0274679661
+epoch=11 global_step=21500 optimizer_step=1341 loss=2.0865135193
+epoch=11 global_step=21600 optimizer_step=1347 loss=2.0664215088
+epoch=11 global_step=21700 optimizer_step=1354 loss=2.0259120464
+epoch=11 global_step=21800 optimizer_step=1360 loss=2.0249927044
+epoch=11 global_step=21900 optimizer_step=1366 loss=2.0943410397
+epoch=11 global_step=22000 optimizer_step=1372 loss=2.1218085289
+epoch=11 global_step=22100 optimizer_step=1379 loss=2.0602319241
+epoch=11 global_step=22200 optimizer_step=1385 loss=2.0149722099
+epoch=11 global_step=22300 optimizer_step=1391 loss=2.0779480934
+epoch=11 global_step=22400 optimizer_step=1397 loss=2.0102200508
+epoch=11 global_step=22500 optimizer_step=1404 loss=2.0085160732
+epoch=12 global_step=22600 optimizer_step=1410 loss=1.9726082087
+epoch=12 global_step=22700 optimizer_step=1416 loss=1.9908233881
+epoch=12 global_step=22800 optimizer_step=1422 loss=1.9168190956
+epoch=12 global_step=22900 optimizer_step=1428 loss=2.0700583458
+epoch=12 global_step=23000 optimizer_step=1435 loss=1.9362208843
+epoch=12 global_step=23100 optimizer_step=1441 loss=1.9807136059
+epoch=12 global_step=23200 optimizer_step=1447 loss=1.9990558624
+epoch=12 global_step=23300 optimizer_step=1453 loss=1.9628033638
+epoch=12 global_step=23400 optimizer_step=1460 loss=2.0686337948
+epoch=12 global_step=23500 optimizer_step=1466 loss=1.9760959148
+epoch=12 global_step=23600 optimizer_step=1472 loss=1.9263136387
+epoch=12 global_step=23700 optimizer_step=1478 loss=1.9407770634
+epoch=12 global_step=23800 optimizer_step=1485 loss=2.1439068317
+epoch=12 global_step=23900 optimizer_step=1491 loss=1.9618707895
+epoch=12 global_step=24000 optimizer_step=1497 loss=1.9036010504
+epoch=12 global_step=24100 optimizer_step=1503 loss=2.0617311001
+epoch=12 global_step=24200 optimizer_step=1510 loss=1.9608662128
+epoch=12 global_step=24300 optimizer_step=1516 loss=1.9213581085
+epoch=13 global_step=24400 optimizer_step=1522 loss=1.9485650063
+epoch=13 global_step=24500 optimizer_step=1528 loss=1.9479918480
+epoch=13 global_step=24600 optimizer_step=1535 loss=1.9401965141
+epoch=13 global_step=24700 optimizer_step=1541 loss=2.0818445683
+epoch=13 global_step=24800 optimizer_step=1547 loss=1.9621839523
+epoch=13 global_step=24900 optimizer_step=1553 loss=1.9257485867
+epoch=13 global_step=25000 optimizer_step=1560 loss=2.0088844299
+epoch=13 global_step=25100 optimizer_step=1566 loss=2.0136649609
+epoch=13 global_step=25200 optimizer_step=1572 loss=1.9189916849
+epoch=13 global_step=25300 optimizer_step=1578 loss=2.0322787762
+epoch=13 global_step=25400 optimizer_step=1585 loss=1.9875651598
+epoch=13 global_step=25500 optimizer_step=1591 loss=1.9721043110
+epoch=13 global_step=25600 optimizer_step=1597 loss=1.8964664936
+epoch=13 global_step=25700 optimizer_step=1603 loss=1.9004751444
+epoch=13 global_step=25800 optimizer_step=1610 loss=1.8928580284
+epoch=13 global_step=25900 optimizer_step=1616 loss=1.9920513630
+epoch=13 global_step=26000 optimizer_step=1622 loss=2.0428643227
+epoch=13 global_step=26100 optimizer_step=1628 loss=2.0103039742
+epoch=13 global_step=26200 optimizer_step=1635 loss=2.1044478416
+epoch=14 global_step=26300 optimizer_step=1641 loss=1.9214316607
+epoch=14 global_step=26400 optimizer_step=1647 loss=1.9417490959
+epoch=14 global_step=26500 optimizer_step=1653 loss=1.9119746685
+epoch=14 global_step=26600 optimizer_step=1659 loss=1.8600076437
+epoch=14 global_step=26700 optimizer_step=1666 loss=1.9327063560
+epoch=14 global_step=26800 optimizer_step=1672 loss=2.0375277996
+epoch=14 global_step=26900 optimizer_step=1678 loss=1.8824788332
+epoch=14 global_step=27000 optimizer_step=1684 loss=1.9575517178
+epoch=14 global_step=27100 optimizer_step=1691 loss=1.9775462151
+epoch=14 global_step=27200 optimizer_step=1697 loss=1.9809827805
+epoch=14 global_step=27300 optimizer_step=1703 loss=1.8648720980
+epoch=14 global_step=27400 optimizer_step=1709 loss=1.9893648624
+epoch=14 global_step=27500 optimizer_step=1716 loss=1.9178037643
+epoch=14 global_step=27600 optimizer_step=1722 loss=1.9179698229
+epoch=14 global_step=27700 optimizer_step=1728 loss=1.9240183830
+epoch=14 global_step=27800 optimizer_step=1734 loss=2.0234532356
+epoch=14 global_step=27900 optimizer_step=1741 loss=1.9561401606
+epoch=14 global_step=28000 optimizer_step=1747 loss=1.9147893190
+epoch=14 global_step=28100 optimizer_step=1753 loss=1.9246246815
+epoch=15 global_step=28200 optimizer_step=1759 loss=1.8739801645
+epoch=15 global_step=28300 optimizer_step=1765 loss=1.8108698130
+epoch=15 global_step=28400 optimizer_step=1772 loss=1.9213745594
+epoch=15 global_step=28500 optimizer_step=1778 loss=1.8882020712
+epoch=15 global_step=28600 optimizer_step=1784 loss=1.9689260721
+epoch=15 global_step=28700 optimizer_step=1790 loss=1.9704325199
+epoch=15 global_step=28800 optimizer_step=1797 loss=1.9746195078
+epoch=15 global_step=28900 optimizer_step=1803 loss=1.8518563509
+epoch=15 global_step=29000 optimizer_step=1809 loss=1.9250388145
+epoch=15 global_step=29100 optimizer_step=1815 loss=2.0425901413
+epoch=15 global_step=29200 optimizer_step=1822 loss=1.9035264254
+epoch=15 global_step=29300 optimizer_step=1828 loss=1.9627593756
+epoch=15 global_step=29400 optimizer_step=1834 loss=1.9363044500
+epoch=15 global_step=29500 optimizer_step=1840 loss=1.9128087759
+epoch=15 global_step=29600 optimizer_step=1847 loss=1.8373038769
+epoch=15 global_step=29700 optimizer_step=1853 loss=1.9265266657
+epoch=15 global_step=29800 optimizer_step=1859 loss=1.9100403786
+epoch=15 global_step=29900 optimizer_step=1865 loss=2.0152709484
+epoch=15 global_step=30000 optimizer_step=1872 loss=1.9183402061
+epoch=16 global_step=30100 optimizer_step=1878 loss=1.9086118937
+epoch=16 global_step=30200 optimizer_step=1884 loss=1.8494266272
+epoch=16 global_step=30300 optimizer_step=1890 loss=1.8829007149
+epoch=16 global_step=30400 optimizer_step=1896 loss=1.8719937801
+epoch=16 global_step=30500 optimizer_step=1903 loss=1.9172031879
+epoch=16 global_step=30600 optimizer_step=1909 loss=1.8617328405
+epoch=16 global_step=30700 optimizer_step=1915 loss=1.8993945122
+epoch=16 global_step=30800 optimizer_step=1921 loss=1.8946076632
+epoch=16 global_step=30900 optimizer_step=1928 loss=1.9591100216
+epoch=16 global_step=31000 optimizer_step=1934 loss=1.8603478670
+epoch=16 global_step=31100 optimizer_step=1940 loss=1.8978595734
+epoch=16 global_step=31200 optimizer_step=1946 loss=1.8258063793
+epoch=16 global_step=31300 optimizer_step=1953 loss=1.8879218102
+epoch=16 global_step=31400 optimizer_step=1959 loss=1.8105870485
+epoch=16 global_step=31500 optimizer_step=1965 loss=1.8639843464
+epoch=16 global_step=31600 optimizer_step=1971 loss=1.9996428490
+epoch=16 global_step=31700 optimizer_step=1978 loss=1.9164056778
+epoch=16 global_step=31800 optimizer_step=1984 loss=1.8956096172
+epoch=17 global_step=31900 optimizer_step=1990 loss=1.8224403858
+epoch=17 global_step=32000 optimizer_step=1996 loss=1.8513727188
+epoch=17 global_step=32100 optimizer_step=2003 loss=1.9286018610
+epoch=17 global_step=32200 optimizer_step=2009 loss=1.7495142221
+epoch=17 global_step=32300 optimizer_step=2015 loss=1.8749437332
+epoch=17 global_step=32400 optimizer_step=2021 loss=1.7982702255
+epoch=17 global_step=32500 optimizer_step=2028 loss=1.8355945349
+epoch=17 global_step=32600 optimizer_step=2034 loss=1.8364803791
+epoch=17 global_step=32700 optimizer_step=2040 loss=1.8635663986
+epoch=17 global_step=32800 optimizer_step=2046 loss=1.9396638870
+epoch=17 global_step=32900 optimizer_step=2053 loss=1.8533239365
+epoch=17 global_step=33000 optimizer_step=2059 loss=1.8377062082
+epoch=17 global_step=33100 optimizer_step=2065 loss=1.9230837822
+epoch=17 global_step=33200 optimizer_step=2071 loss=1.8086023331
+epoch=17 global_step=33300 optimizer_step=2078 loss=1.9231770039
+epoch=17 global_step=33400 optimizer_step=2084 loss=1.7682596445
+epoch=17 global_step=33500 optimizer_step=2090 loss=1.7871932983
+epoch=17 global_step=33600 optimizer_step=2096 loss=1.8538557291
+epoch=17 global_step=33700 optimizer_step=2103 loss=1.9055104256
+epoch=18 global_step=33800 optimizer_step=2109 loss=1.8163551092
+epoch=18 global_step=33900 optimizer_step=2115 loss=1.8340356350
+epoch=18 global_step=34000 optimizer_step=2121 loss=1.8167200089
+epoch=18 global_step=34100 optimizer_step=2127 loss=1.8663976192
+epoch=18 global_step=34200 optimizer_step=2134 loss=1.8014510870
+epoch=18 global_step=34300 optimizer_step=2140 loss=1.8339885473
+epoch=18 global_step=34400 optimizer_step=2146 loss=1.8029958010
+epoch=18 global_step=34500 optimizer_step=2152 loss=1.8743531704
+epoch=18 global_step=34600 optimizer_step=2159 loss=1.7688024044
+epoch=18 global_step=34700 optimizer_step=2165 loss=1.8701403141
+epoch=18 global_step=34800 optimizer_step=2171 loss=1.7610011101
+epoch=18 global_step=34900 optimizer_step=2177 loss=1.7626130581
+epoch=18 global_step=35000 optimizer_step=2184 loss=1.8226894140
+epoch=18 global_step=35100 optimizer_step=2190 loss=1.7491966486
+epoch=18 global_step=35200 optimizer_step=2196 loss=1.8771066666
+epoch=18 global_step=35300 optimizer_step=2202 loss=1.8555011749
+epoch=18 global_step=35400 optimizer_step=2209 loss=1.7629066706
+epoch=18 global_step=35500 optimizer_step=2215 loss=1.7591476440
+epoch=18 global_step=35600 optimizer_step=2221 loss=1.8556770086
+epoch=19 global_step=35700 optimizer_step=2227 loss=1.8963214159
+epoch=19 global_step=35800 optimizer_step=2233 loss=1.8888378143
+epoch=19 global_step=35900 optimizer_step=2240 loss=1.8287310600
+epoch=19 global_step=36000 optimizer_step=2246 loss=1.7227777243
+epoch=19 global_step=36100 optimizer_step=2252 loss=1.7600711584
+epoch=19 global_step=36200 optimizer_step=2258 loss=1.8546459675
+epoch=19 global_step=36300 optimizer_step=2265 loss=2.0286033154
+epoch=19 global_step=36400 optimizer_step=2271 loss=1.8558450937
+epoch=19 global_step=36500 optimizer_step=2277 loss=1.8852148056
+epoch=19 global_step=36600 optimizer_step=2283 loss=1.7895061970
+epoch=19 global_step=36700 optimizer_step=2290 loss=1.7849118710
+epoch=19 global_step=36800 optimizer_step=2296 loss=1.8016135693
+epoch=19 global_step=36900 optimizer_step=2302 loss=1.8018785715
+epoch=19 global_step=37000 optimizer_step=2308 loss=1.7718360424
+epoch=19 global_step=37100 optimizer_step=2315 loss=1.8767540455
+epoch=19 global_step=37200 optimizer_step=2321 loss=1.7227754593
+epoch=19 global_step=37300 optimizer_step=2327 loss=1.8910079002
+epoch=19 global_step=37400 optimizer_step=2333 loss=1.7912203074
+epoch=19 global_step=37500 optimizer_step=2340 loss=1.8723261356