Training in progress, epoch 1, checkpoint

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text

last-checkpoint/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
+}

last-checkpoint/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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 %}

last-checkpoint/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.53.3"
+}

last-checkpoint/global_step548/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea983d7491688a0552b3da916b5a27fdded4c049f300653e4613b5fc6e45cd6
+size 15231238785

last-checkpoint/global_step548/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84ff4803e050b2baa600256daeaed70209b10da80cfeac246152bda1640cbed0
+size 15231238785

last-checkpoint/global_step548/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b825f7ca7c788b5126430d26960ae7f530ee86bcf34e92df9b97d4a74e25c12
+size 15231238785

last-checkpoint/global_step548/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcad61a5ceb64ff1a0126c2f0e35219b7a6cf269167387a5dc839e246b417927
+size 15231238785

last-checkpoint/global_step548/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfd2d47fdc7c492c9b3839800aad7cbc32a34b316cad7d49eceae3529f84d20d
+size 166752

last-checkpoint/global_step548/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b674de1a790cd800fe11bd9a09d5109af8b3cf0286f823f85f71bf007290ddac
+size 166752

last-checkpoint/global_step548/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb0733dd6c787de73648ca4373e8e7b552f88b77f685f7fad97d68cfbe2d700b
+size 166752

last-checkpoint/global_step548/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b580a4016c7215787acfa0d4a199d32c40c7309a90b7428b87b425c0caf898
+size 166752

last-checkpoint/latest

@@ -0,0 +1 @@
+global_step548

last-checkpoint/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80521f6c900143697281d4600e67ab315c8b71bceacee150223128239ef99971
+size 4877660776

last-checkpoint/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d128d9387aa00a908f5968a815f0cef17c472e7d1e80e69541de184041a20f31
+size 4932751008

last-checkpoint/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dd6ca393d0c46fcf5d9d2480065f288ab16af2e24809caaffb4d02dec32aa4c
+size 4330865200

last-checkpoint/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6044a4ba978cea9f0c0999cc35796dd6b3ddb394eaf324bd9a97964684038828
+size 1089994880

last-checkpoint/model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 333312,
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe6b873f1da64bb980afe982fc1c6b6bc461ad8c33073d856804323f64b26d9
+size 15429

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13db4dd10b22b5464f5ef0b539152b46390eae6a827b355108cb54b1af2eb830
+size 15429

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e293f13fb6e873e8081636b6b07115410b397c55f1ed08b8772b059c8eb74e
+size 15429

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c595c077664f94b7f91088561951be20e39483e01865774a83bc46f3971a3152
+size 15429

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f5b063c2f54dad51b7840e2f9b7461a9e5e558bbc9181e07f8ad10df71ba3e
+size 1465

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.json

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

last-checkpoint/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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,875 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 548,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0018248175182481751,
+      "grad_norm": 183.4268798763667,
+      "learning_rate": 0.0,
+      "logits/chosen": -0.486328125,
+      "logits/rejected": -0.65234375,
+      "logps/chosen": -1016.0,
+      "logps/rejected": -908.0,
+      "loss": 0.6914,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.01824817518248175,
+      "grad_norm": 190.79059532204576,
+      "learning_rate": 8.181818181818182e-08,
+      "logits/chosen": -0.9583333134651184,
+      "logits/rejected": -0.8624131679534912,
+      "logps/chosen": -399.3333435058594,
+      "logps/rejected": -353.1111145019531,
+      "loss": 0.7228,
+      "rewards/accuracies": 0.1805555522441864,
+      "rewards/chosen": -0.01952446810901165,
+      "rewards/margins": -0.0528903529047966,
+      "rewards/rejected": 0.0333658866584301,
+      "step": 10
+    },
+    {
+      "epoch": 0.0364963503649635,
+      "grad_norm": 200.0933911782489,
+      "learning_rate": 1.7272727272727272e-07,
+      "logits/chosen": -0.7900390625,
+      "logits/rejected": -0.792773425579071,
+      "logps/chosen": -512.0,
+      "logps/rejected": -455.79998779296875,
+      "loss": 0.6865,
+      "rewards/accuracies": 0.3499999940395355,
+      "rewards/chosen": 0.09881591796875,
+      "rewards/margins": 0.02115478552877903,
+      "rewards/rejected": 0.07758178561925888,
+      "step": 20
+    },
+    {
+      "epoch": 0.05474452554744526,
+      "grad_norm": 137.2607562201183,
+      "learning_rate": 2.636363636363636e-07,
+      "logits/chosen": -0.839160144329071,
+      "logits/rejected": -0.898242175579071,
+      "logps/chosen": -380.6000061035156,
+      "logps/rejected": -331.3999938964844,
+      "loss": 0.6383,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.5669921636581421,
+      "rewards/margins": 0.1439208984375,
+      "rewards/rejected": 0.4232421815395355,
+      "step": 30
+    },
+    {
+      "epoch": 0.072992700729927,
+      "grad_norm": 83.1602987250809,
+      "learning_rate": 3.545454545454545e-07,
+      "logits/chosen": -0.7520507574081421,
+      "logits/rejected": -0.891796886920929,
+      "logps/chosen": -440.3999938964844,
+      "logps/rejected": -381.79998779296875,
+      "loss": 0.5843,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.085546851158142,
+      "rewards/margins": 0.4743408262729645,
+      "rewards/rejected": 0.61279296875,
+      "step": 40
+    },
+    {
+      "epoch": 0.09124087591240876,
+      "grad_norm": 72.42686849970667,
+      "learning_rate": 4.4545454545454544e-07,
+      "logits/chosen": -0.5654296875,
+      "logits/rejected": -0.6791015863418579,
+      "logps/chosen": -484.0,
+      "logps/rejected": -410.6000061035156,
+      "loss": 0.5111,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.700781226158142,
+      "rewards/margins": 0.850634753704071,
+      "rewards/rejected": 0.850390613079071,
+      "step": 50
+    },
+    {
+      "epoch": 0.10948905109489052,
+      "grad_norm": 85.28805875692137,
+      "learning_rate": 4.959432048681541e-07,
+      "logits/chosen": -0.516406238079071,
+      "logits/rejected": -0.570239245891571,
+      "logps/chosen": -376.79998779296875,
+      "logps/rejected": -328.29998779296875,
+      "loss": 0.437,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 1.7800781726837158,
+      "rewards/margins": 0.961376965045929,
+      "rewards/rejected": 0.818359375,
+      "step": 60
+    },
+    {
+      "epoch": 0.12773722627737227,
+      "grad_norm": 91.08005236458708,
+      "learning_rate": 4.858012170385395e-07,
+      "logits/chosen": -0.46367186307907104,
+      "logits/rejected": -0.4881347715854645,
+      "logps/chosen": -422.6000061035156,
+      "logps/rejected": -347.3999938964844,
+      "loss": 0.5437,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 1.330078125,
+      "rewards/margins": 0.734570324420929,
+      "rewards/rejected": 0.595654308795929,
+      "step": 70
+    },
+    {
+      "epoch": 0.145985401459854,
+      "grad_norm": 96.85867903332033,
+      "learning_rate": 4.7565922920892493e-07,
+      "logits/chosen": -0.4019775390625,
+      "logits/rejected": -0.43791502714157104,
+      "logps/chosen": -455.3999938964844,
+      "logps/rejected": -468.0,
+      "loss": 0.5068,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 1.2746093273162842,
+      "rewards/margins": 0.9996093511581421,
+      "rewards/rejected": 0.27705079317092896,
+      "step": 80
+    },
+    {
+      "epoch": 0.16423357664233576,
+      "grad_norm": 67.75491451556083,
+      "learning_rate": 4.655172413793103e-07,
+      "logits/chosen": -0.24169310927391052,
+      "logits/rejected": -0.29462891817092896,
+      "logps/chosen": -424.3999938964844,
+      "logps/rejected": -374.20001220703125,
+      "loss": 0.3807,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 1.853124976158142,
+      "rewards/margins": 1.2941405773162842,
+      "rewards/rejected": 0.5595703125,
+      "step": 90
+    },
+    {
+      "epoch": 0.18248175182481752,
+      "grad_norm": 93.30496706040954,
+      "learning_rate": 4.5537525354969567e-07,
+      "logits/chosen": -0.23894043266773224,
+      "logits/rejected": -0.25419920682907104,
+      "logps/chosen": -440.0,
+      "logps/rejected": -393.20001220703125,
+      "loss": 0.4229,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 1.433203101158142,
+      "rewards/margins": 1.3212890625,
+      "rewards/rejected": 0.11308594048023224,
+      "step": 100
+    },
+    {
+      "epoch": 0.20072992700729927,
+      "grad_norm": 62.86660194925304,
+      "learning_rate": 4.4523326572008114e-07,
+      "logits/chosen": -0.14438477158546448,
+      "logits/rejected": -0.25579530000686646,
+      "logps/chosen": -409.20001220703125,
+      "logps/rejected": -377.3999938964844,
+      "loss": 0.3675,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 1.952734351158142,
+      "rewards/margins": 1.849218726158142,
+      "rewards/rejected": 0.10541991889476776,
+      "step": 110
+    },
+    {
+      "epoch": 0.21897810218978103,
+      "grad_norm": 60.03776822417948,
+      "learning_rate": 4.350912778904665e-07,
+      "logits/chosen": -0.346923828125,
+      "logits/rejected": -0.3475585877895355,
+      "logps/chosen": -491.0,
+      "logps/rejected": -472.0,
+      "loss": 0.4935,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 1.447265625,
+      "rewards/margins": 1.2218749523162842,
+      "rewards/rejected": 0.22526855766773224,
+      "step": 120
+    },
+    {
+      "epoch": 0.23722627737226276,
+      "grad_norm": 69.45442852616328,
+      "learning_rate": 4.249492900608519e-07,
+      "logits/chosen": -0.17467041313648224,
+      "logits/rejected": -0.20947265625,
+      "logps/chosen": -432.20001220703125,
+      "logps/rejected": -399.0,
+      "loss": 0.468,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 1.036718726158142,
+      "rewards/margins": 1.351953148841858,
+      "rewards/rejected": -0.313507080078125,
+      "step": 130
+    },
+    {
+      "epoch": 0.25547445255474455,
+      "grad_norm": 139.01818106445947,
+      "learning_rate": 4.148073022312373e-07,
+      "logits/chosen": -0.21988525986671448,
+      "logits/rejected": -0.26655274629592896,
+      "logps/chosen": -455.3999938964844,
+      "logps/rejected": -420.0,
+      "loss": 0.372,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 1.1648437976837158,
+      "rewards/margins": 1.658544898033142,
+      "rewards/rejected": -0.4948974549770355,
+      "step": 140
+    },
+    {
+      "epoch": 0.2737226277372263,
+      "grad_norm": 63.738656533900965,
+      "learning_rate": 4.046653144016227e-07,
+      "logits/chosen": -0.140167236328125,
+      "logits/rejected": -0.22265625,
+      "logps/chosen": -373.0,
+      "logps/rejected": -330.70001220703125,
+      "loss": 0.4044,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 1.3445312976837158,
+      "rewards/margins": 1.5832030773162842,
+      "rewards/rejected": -0.23894043266773224,
+      "step": 150
+    },
+    {
+      "epoch": 0.291970802919708,
+      "grad_norm": 58.53887833297566,
+      "learning_rate": 3.945233265720081e-07,
+      "logits/chosen": -0.18510742485523224,
+      "logits/rejected": -0.107086181640625,
+      "logps/chosen": -485.6000061035156,
+      "logps/rejected": -449.0,
+      "loss": 0.5703,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 1.7589843273162842,
+      "rewards/margins": 1.361425757408142,
+      "rewards/rejected": 0.3995117247104645,
+      "step": 160
+    },
+    {
+      "epoch": 0.3102189781021898,
+      "grad_norm": 91.87755966731375,
+      "learning_rate": 3.843813387423935e-07,
+      "logits/chosen": -0.23171386122703552,
+      "logits/rejected": -0.26677244901657104,
+      "logps/chosen": -465.20001220703125,
+      "logps/rejected": -475.20001220703125,
+      "loss": 0.4439,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 1.56640625,
+      "rewards/margins": 1.7265625,
+      "rewards/rejected": -0.15704345703125,
+      "step": 170
+    },
+    {
+      "epoch": 0.3284671532846715,
+      "grad_norm": 101.70063789740826,
+      "learning_rate": 3.7423935091277887e-07,
+      "logits/chosen": -0.06843261420726776,
+      "logits/rejected": -0.13564452528953552,
+      "logps/chosen": -502.20001220703125,
+      "logps/rejected": -482.0,
+      "loss": 0.3524,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 1.283593773841858,
+      "rewards/margins": 1.9167969226837158,
+      "rewards/rejected": -0.63427734375,
+      "step": 180
+    },
+    {
+      "epoch": 0.3467153284671533,
+      "grad_norm": 129.4709446137554,
+      "learning_rate": 3.640973630831643e-07,
+      "logits/chosen": -0.27153319120407104,
+      "logits/rejected": -0.21871337294578552,
+      "logps/chosen": -452.79998779296875,
+      "logps/rejected": -441.0,
+      "loss": 0.502,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 1.521875023841858,
+      "rewards/margins": 1.573339819908142,
+      "rewards/rejected": -0.05205078050494194,
+      "step": 190
+    },
+    {
+      "epoch": 0.36496350364963503,
+      "grad_norm": 52.84176487442608,
+      "learning_rate": 3.5395537525354966e-07,
+      "logits/chosen": 0.02674560621380806,
+      "logits/rejected": -0.009631347842514515,
+      "logps/chosen": -454.20001220703125,
+      "logps/rejected": -382.20001220703125,
+      "loss": 0.4234,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 1.603906273841858,
+      "rewards/margins": 1.7890625,
+      "rewards/rejected": -0.18623046576976776,
+      "step": 200
+    },
+    {
+      "epoch": 0.38321167883211676,
+      "grad_norm": 64.84134129708892,
+      "learning_rate": 3.438133874239351e-07,
+      "logits/chosen": -0.18310546875,
+      "logits/rejected": -0.19301757216453552,
+      "logps/chosen": -411.79998779296875,
+      "logps/rejected": -366.3999938964844,
+      "loss": 0.3577,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 1.482812523841858,
+      "rewards/margins": 1.923437476158142,
+      "rewards/rejected": -0.4388671815395355,
+      "step": 210
+    },
+    {
+      "epoch": 0.40145985401459855,
+      "grad_norm": 105.65792625209929,
+      "learning_rate": 3.3367139959432044e-07,
+      "logits/chosen": -0.09575805813074112,
+      "logits/rejected": -0.14519043266773224,
+      "logps/chosen": -443.20001220703125,
+      "logps/rejected": -427.79998779296875,
+      "loss": 0.4191,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 1.326562523841858,
+      "rewards/margins": 1.966796875,
+      "rewards/rejected": -0.6392577886581421,
+      "step": 220
+    },
+    {
+      "epoch": 0.4197080291970803,
+      "grad_norm": 109.72645289364215,
+      "learning_rate": 3.2352941176470586e-07,
+      "logits/chosen": 0.01968994177877903,
+      "logits/rejected": -0.03289794921875,
+      "logps/chosen": -485.6000061035156,
+      "logps/rejected": -453.20001220703125,
+      "loss": 0.4353,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 1.896875023841858,
+      "rewards/margins": 1.94921875,
+      "rewards/rejected": -0.05209960788488388,
+      "step": 230
+    },
+    {
+      "epoch": 0.43795620437956206,
+      "grad_norm": 54.27538060537205,
+      "learning_rate": 3.133874239350913e-07,
+      "logits/chosen": -0.21235351264476776,
+      "logits/rejected": -0.23594971001148224,
+      "logps/chosen": -502.0,
+      "logps/rejected": -472.20001220703125,
+      "loss": 0.2759,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 1.908203125,
+      "rewards/margins": 2.317187547683716,
+      "rewards/rejected": -0.40947264432907104,
+      "step": 240
+    },
+    {
+      "epoch": 0.4562043795620438,
+      "grad_norm": 209.29865250933202,
+      "learning_rate": 3.0324543610547665e-07,
+      "logits/chosen": 0.01799316331744194,
+      "logits/rejected": 0.07851867377758026,
+      "logps/chosen": -444.6000061035156,
+      "logps/rejected": -399.6000061035156,
+      "loss": 0.4111,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 2.125,
+      "rewards/margins": 2.1265625953674316,
+      "rewards/rejected": -0.0016113281017169356,
+      "step": 250
+    },
+    {
+      "epoch": 0.4744525547445255,
+      "grad_norm": 72.97301814642577,
+      "learning_rate": 2.93103448275862e-07,
+      "logits/chosen": 0.03842773288488388,
+      "logits/rejected": 0.01112976111471653,
+      "logps/chosen": -445.0,
+      "logps/rejected": -411.0,
+      "loss": 0.4229,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 1.3894531726837158,
+      "rewards/margins": 1.676855444908142,
+      "rewards/rejected": -0.28840333223342896,
+      "step": 260
+    },
+    {
+      "epoch": 0.4927007299270073,
+      "grad_norm": 100.52100065549308,
+      "learning_rate": 2.829614604462475e-07,
+      "logits/chosen": 0.04062499850988388,
+      "logits/rejected": -0.05421142652630806,
+      "logps/chosen": -457.3999938964844,
+      "logps/rejected": -447.79998779296875,
+      "loss": 0.5097,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 1.5515625476837158,
+      "rewards/margins": 1.6711914539337158,
+      "rewards/rejected": -0.1171875,
+      "step": 270
+    },
+    {
+      "epoch": 0.5109489051094891,
+      "grad_norm": 71.42885032223506,
+      "learning_rate": 2.7281947261663286e-07,
+      "logits/chosen": -0.0455322265625,
+      "logits/rejected": -0.01320800743997097,
+      "logps/chosen": -512.2000122070312,
+      "logps/rejected": -464.3999938964844,
+      "loss": 0.4505,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 1.1550781726837158,
+      "rewards/margins": 1.8136718273162842,
+      "rewards/rejected": -0.6611328125,
+      "step": 280
+    },
+    {
+      "epoch": 0.5291970802919708,
+      "grad_norm": 72.23719994945806,
+      "learning_rate": 2.6267748478701823e-07,
+      "logits/chosen": -0.14443358778953552,
+      "logits/rejected": -0.14687499403953552,
+      "logps/chosen": -442.79998779296875,
+      "logps/rejected": -440.79998779296875,
+      "loss": 0.3643,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 1.404394507408142,
+      "rewards/margins": 2.530468702316284,
+      "rewards/rejected": -1.126562476158142,
+      "step": 290
+    },
+    {
+      "epoch": 0.5474452554744526,
+      "grad_norm": 109.10421493067516,
+      "learning_rate": 2.525354969574036e-07,
+      "logits/chosen": 0.01424560509622097,
+      "logits/rejected": 0.12192382663488388,
+      "logps/chosen": -592.4000244140625,
+      "logps/rejected": -598.0,
+      "loss": 0.3889,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 0.956250011920929,
+      "rewards/margins": 2.1015625,
+      "rewards/rejected": -1.142822265625,
+      "step": 300
+    },
+    {
+      "epoch": 0.5656934306569343,
+      "grad_norm": 86.4722981606142,
+      "learning_rate": 2.42393509127789e-07,
+      "logits/chosen": -0.06550292670726776,
+      "logits/rejected": -0.04240722581744194,
+      "logps/chosen": -473.20001220703125,
+      "logps/rejected": -456.3999938964844,
+      "loss": 0.4345,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.6993774175643921,
+      "rewards/margins": 1.698828101158142,
+      "rewards/rejected": -0.9986327886581421,
+      "step": 310
+    },
+    {
+      "epoch": 0.583941605839416,
+      "grad_norm": 57.2804545162538,
+      "learning_rate": 2.3225152129817443e-07,
+      "logits/chosen": 0.05268554762005806,
+      "logits/rejected": 0.06523437798023224,
+      "logps/chosen": -429.20001220703125,
+      "logps/rejected": -381.3999938964844,
+      "loss": 0.3993,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.7642577886581421,
+      "rewards/margins": 1.9884765148162842,
+      "rewards/rejected": -1.222021460533142,
+      "step": 320
+    },
+    {
+      "epoch": 0.6021897810218978,
+      "grad_norm": 170.96405372232695,
+      "learning_rate": 2.2210953346855983e-07,
+      "logits/chosen": -0.09375,
+      "logits/rejected": -0.18121948838233948,
+      "logps/chosen": -411.20001220703125,
+      "logps/rejected": -421.20001220703125,
+      "loss": 0.3965,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.908007800579071,
+      "rewards/margins": 1.976171851158142,
+      "rewards/rejected": -1.068359375,
+      "step": 330
+    },
+    {
+      "epoch": 0.6204379562043796,
+      "grad_norm": 93.61816587541509,
+      "learning_rate": 2.1196754563894522e-07,
+      "logits/chosen": -0.10378418117761612,
+      "logits/rejected": -0.03239746019244194,
+      "logps/chosen": -440.3999938964844,
+      "logps/rejected": -413.79998779296875,
+      "loss": 0.5115,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 0.719970703125,
+      "rewards/margins": 1.680078148841858,
+      "rewards/rejected": -0.9598633050918579,
+      "step": 340
+    },
+    {
+      "epoch": 0.6386861313868614,
+      "grad_norm": 92.84152158463883,
+      "learning_rate": 2.0182555780933062e-07,
+      "logits/chosen": -0.08485107123851776,
+      "logits/rejected": -0.09698486328125,
+      "logps/chosen": -468.3999938964844,
+      "logps/rejected": -484.0,
+      "loss": 0.4151,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 0.4109863340854645,
+      "rewards/margins": 2.1148438453674316,
+      "rewards/rejected": -1.707421898841858,
+      "step": 350
+    },
+    {
+      "epoch": 0.656934306569343,
+      "grad_norm": 116.66381358621938,
+      "learning_rate": 1.91683569979716e-07,
+      "logits/chosen": -0.047119140625,
+      "logits/rejected": -0.0908203125,
+      "logps/chosen": -523.4000244140625,
+      "logps/rejected": -520.4000244140625,
+      "loss": 0.4036,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.7984374761581421,
+      "rewards/margins": 1.9406249523162842,
+      "rewards/rejected": -1.1416015625,
+      "step": 360
+    },
+    {
+      "epoch": 0.6751824817518248,
+      "grad_norm": 66.21210834363939,
+      "learning_rate": 1.815415821501014e-07,
+      "logits/chosen": 0.01052246056497097,
+      "logits/rejected": 0.00347900390625,
+      "logps/chosen": -443.3999938964844,
+      "logps/rejected": -418.6000061035156,
+      "loss": 0.4784,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.4449218809604645,
+      "rewards/margins": 1.796484351158142,
+      "rewards/rejected": -1.3522460460662842,
+      "step": 370
+    },
+    {
+      "epoch": 0.6934306569343066,
+      "grad_norm": 96.94205645326319,
+      "learning_rate": 1.7139959432048682e-07,
+      "logits/chosen": -0.06866760551929474,
+      "logits/rejected": -0.07124023139476776,
+      "logps/chosen": -450.6000061035156,
+      "logps/rejected": -419.5,
+      "loss": 0.4503,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 0.5906738042831421,
+      "rewards/margins": 1.701171875,
+      "rewards/rejected": -1.1095702648162842,
+      "step": 380
+    },
+    {
+      "epoch": 0.7116788321167883,
+      "grad_norm": 170.19556173050714,
+      "learning_rate": 1.612576064908722e-07,
+      "logits/chosen": -0.02810058556497097,
+      "logits/rejected": 0.04189453274011612,
+      "logps/chosen": -413.6000061035156,
+      "logps/rejected": -385.79998779296875,
+      "loss": 0.383,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 0.6146484613418579,
+      "rewards/margins": 2.09375,
+      "rewards/rejected": -1.4822266101837158,
+      "step": 390
+    },
+    {
+      "epoch": 0.7299270072992701,
+      "grad_norm": 200.81203370210167,
+      "learning_rate": 1.511156186612576e-07,
+      "logits/chosen": 0.02833252027630806,
+      "logits/rejected": -0.02805175818502903,
+      "logps/chosen": -447.0,
+      "logps/rejected": -401.20001220703125,
+      "loss": 0.4363,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 1.0343506336212158,
+      "rewards/margins": 2.0367188453674316,
+      "rewards/rejected": -1.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.7481751824817519,
+      "grad_norm": 128.18451740094875,
+      "learning_rate": 1.4097363083164298e-07,
+      "logits/chosen": -0.083251953125,
+      "logits/rejected": -0.05070800706744194,
+      "logps/chosen": -457.0,
+      "logps/rejected": -417.79998779296875,
+      "loss": 0.4099,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 1.0426757335662842,
+      "rewards/margins": 2.3359375,
+      "rewards/rejected": -1.2976562976837158,
+      "step": 410
+    },
+    {
+      "epoch": 0.7664233576642335,
+      "grad_norm": 122.2923701591513,
+      "learning_rate": 1.308316430020284e-07,
+      "logits/chosen": 0.02608642540872097,
+      "logits/rejected": -0.01593627966940403,
+      "logps/chosen": -380.6000061035156,
+      "logps/rejected": -373.79998779296875,
+      "loss": 0.4059,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.92529296875,
+      "rewards/margins": 2.4878907203674316,
+      "rewards/rejected": -1.5636718273162842,
+      "step": 420
+    },
+    {
+      "epoch": 0.7846715328467153,
+      "grad_norm": 171.12346779236017,
+      "learning_rate": 1.206896551724138e-07,
+      "logits/chosen": 0.24042968451976776,
+      "logits/rejected": 0.085296630859375,
+      "logps/chosen": -383.6000061035156,
+      "logps/rejected": -373.79998779296875,
+      "loss": 0.4154,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.9688720703125,
+      "rewards/margins": 2.010937452316284,
+      "rewards/rejected": -1.0431640148162842,
+      "step": 430
+    },
+    {
+      "epoch": 0.8029197080291971,
+      "grad_norm": 90.24483614578641,
+      "learning_rate": 1.1054766734279918e-07,
+      "logits/chosen": -0.05828857421875,
+      "logits/rejected": -0.06459961086511612,
+      "logps/chosen": -411.20001220703125,
+      "logps/rejected": -397.0,
+      "loss": 0.4134,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.1129882335662842,
+      "rewards/margins": 1.866796851158142,
+      "rewards/rejected": -0.749707043170929,
+      "step": 440
+    },
+    {
+      "epoch": 0.8211678832116789,
+      "grad_norm": 26.93997549104036,
+      "learning_rate": 1.0040567951318458e-07,
+      "logits/chosen": -0.16145019233226776,
+      "logits/rejected": -0.169921875,
+      "logps/chosen": -453.20001220703125,
+      "logps/rejected": -431.0,
+      "loss": 0.2786,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 1.112890601158142,
+      "rewards/margins": 2.4312500953674316,
+      "rewards/rejected": -1.3162109851837158,
+      "step": 450
+    },
+    {
+      "epoch": 0.8394160583941606,
+      "grad_norm": 59.45894612144818,
+      "learning_rate": 9.026369168356999e-08,
+      "logits/chosen": 0.0780029296875,
+      "logits/rejected": 0.05783691257238388,
+      "logps/chosen": -441.0,
+      "logps/rejected": -403.3999938964844,
+      "loss": 0.3064,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 1.163671851158142,
+      "rewards/margins": 2.453125,
+      "rewards/rejected": -1.2890625,
+      "step": 460
+    },
+    {
+      "epoch": 0.8576642335766423,
+      "grad_norm": 80.72693168394458,
+      "learning_rate": 8.012170385395538e-08,
+      "logits/chosen": 0.06926269829273224,
+      "logits/rejected": -0.0065063475631177425,
+      "logps/chosen": -476.6000061035156,
+      "logps/rejected": -449.6000061035156,
+      "loss": 0.5556,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.7232666015625,
+      "rewards/margins": 1.98828125,
+      "rewards/rejected": -1.266259789466858,
+      "step": 470
+    },
+    {
+      "epoch": 0.8759124087591241,
+      "grad_norm": 28.20404376922917,
+      "learning_rate": 6.997971602434077e-08,
+      "logits/chosen": -0.02747192420065403,
+      "logits/rejected": 0.05877685546875,
+      "logps/chosen": -389.0,
+      "logps/rejected": -377.79998779296875,
+      "loss": 0.3302,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 1.2389647960662842,
+      "rewards/margins": 2.2281250953674316,
+      "rewards/rejected": -0.9869140386581421,
+      "step": 480
+    },
+    {
+      "epoch": 0.8941605839416058,
+      "grad_norm": 70.22161951421818,
+      "learning_rate": 5.983772819472617e-08,
+      "logits/chosen": -0.07192382961511612,
+      "logits/rejected": -0.06147461012005806,
+      "logps/chosen": -445.79998779296875,
+      "logps/rejected": -437.6000061035156,
+      "loss": 0.4594,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 1.417871117591858,
+      "rewards/margins": 1.9235351085662842,
+      "rewards/rejected": -0.505908191204071,
+      "step": 490
+    },
+    {
+      "epoch": 0.9124087591240876,
+      "grad_norm": 153.0002143782165,
+      "learning_rate": 4.969574036511156e-08,
+      "logits/chosen": 0.06987304985523224,
+      "logits/rejected": 0.007641601376235485,
+      "logps/chosen": -420.3999938964844,
+      "logps/rejected": -338.79998779296875,
+      "loss": 0.3153,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 1.2451171875,
+      "rewards/margins": 2.368359327316284,
+      "rewards/rejected": -1.123925805091858,
+      "step": 500
+    },
+    {
+      "epoch": 0.9306569343065694,
+      "grad_norm": 291.65840516029397,
+      "learning_rate": 3.9553752535496954e-08,
+      "logits/chosen": -0.06279297173023224,
+      "logits/rejected": -0.05703125149011612,
+      "logps/chosen": -430.6000061035156,
+      "logps/rejected": -369.0,
+      "loss": 0.3813,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 1.338476538658142,
+      "rewards/margins": 2.424999952316284,
+      "rewards/rejected": -1.08837890625,
+      "step": 510
+    },
+    {
+      "epoch": 0.948905109489051,
+      "grad_norm": 79.85392566108807,
+      "learning_rate": 2.941176470588235e-08,
+      "logits/chosen": -0.18828125298023224,
+      "logits/rejected": -0.16739502549171448,
+      "logps/chosen": -429.3999938964844,
+      "logps/rejected": -395.0,
+      "loss": 0.315,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 1.3271484375,
+      "rewards/margins": 2.3125,
+      "rewards/rejected": -0.988525390625,
+      "step": 520
+    },
+    {
+      "epoch": 0.9671532846715328,
+      "grad_norm": 139.5351558966506,
+      "learning_rate": 1.9269776876267748e-08,
+      "logits/chosen": -0.09885253757238388,
+      "logits/rejected": -0.02666015550494194,
+      "logps/chosen": -443.3999938964844,
+      "logps/rejected": -425.6000061035156,
+      "loss": 0.3221,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 1.400390625,
+      "rewards/margins": 2.6953125,
+      "rewards/rejected": -1.2951171398162842,
+      "step": 530
+    },
+    {
+      "epoch": 0.9854014598540146,
+      "grad_norm": 23.962818117622025,
+      "learning_rate": 9.127789046653143e-09,
+      "logits/chosen": 0.04451904445886612,
+      "logits/rejected": 0.0567626953125,
+      "logps/chosen": -394.0,
+      "logps/rejected": -396.6000061035156,
+      "loss": 0.3834,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": 0.765002429485321,
+      "rewards/margins": 1.690332055091858,
+      "rewards/rejected": -0.9234374761581421,
+      "step": 540
+    },
+    {
+      "epoch": 1.0,
+      "eval_logits/chosen": -0.07358022779226303,
+      "eval_logits/rejected": -0.09998497366905212,
+      "eval_logps/chosen": -466.1538391113281,
+      "eval_logps/rejected": -437.0,
+      "eval_loss": 0.392181396484375,
+      "eval_rewards/accuracies": 0.7403846383094788,
+      "eval_rewards/chosen": 0.7243840098381042,
+      "eval_rewards/margins": 2.152644157409668,
+      "eval_rewards/rejected": -1.426832914352417,
+      "eval_runtime": 8.2786,
+      "eval_samples_per_second": 12.079,
+      "eval_steps_per_second": 1.57,
+      "step": 548
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 548,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccc6d6d6ccc6a292c50503464ca786831eb0e733dd5749ac08f3274417aa7436
+size 8401

last-checkpoint/zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)