Upload folder using huggingface_hub

.gitattributes

@@ -42,3 +42,5 @@ SDPO-train32-alpha0.5-rollout8-lr1e-5-bigmath-Qwen-Qwen3-1.7B/global_step_60/act
 SDPO-train32-alpha0.5-rollout8-lr1e-5-bigmath-Qwen-Qwen3-1.7B/global_step_70/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 SDPO-train32-alpha0.5-rollout8-lr1e-5-bigmath-Qwen-Qwen3-1.7B/global_step_80/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen3-1.7b-sft-lora/checkpoint-9752/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen3-1.7b-sft/checkpoint-6502/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen3-1.7b-sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen3-1.7b-sft/README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen3-1.7B-Base
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen3-1.7b-sft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen3-1.7b-sft
+
+This model is a fine-tuned version of [Qwen/Qwen3-1.7B-Base](https://huggingface.co/Qwen/Qwen3-1.7B-Base) on the mobilek2_sft1 and the mobilek2_sft2 datasets.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 48
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 96
+- total_eval_batch_size: 384
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.7.0+rocm6.3
+- Datasets 4.0.0
+- Tokenizers 0.21.4

qwen3-1.7b-sft/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

qwen3-1.7b-sft/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 7602235458453504.0,
+    "train_loss": 0.4130896302561729,
+    "train_runtime": 242271.9548,
+    "train_samples_per_second": 2.576,
+    "train_steps_per_second": 0.027
+}

qwen3-1.7b-sft/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

qwen3-1.7b-sft/checkpoint-6502/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

qwen3-1.7b-sft/checkpoint-6502/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

qwen3-1.7b-sft/checkpoint-6502/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

qwen3-1.7b-sft/checkpoint-6502/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.52.4"
+}

qwen3-1.7b-sft/checkpoint-6502/global_step6502/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:bb783c8f298187ac41585f65b50d7c7d960954d24378f2b331c9234f1dabe640
+size 430150469

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b4638b6aea0f339baa807d460f6e4e9b5746dabb18b5b1d8bb872a1b561a614
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:684f021b026eb54f9800a4306738bd2962c288b0f390eae6c59eed121bd79f7e
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d37f19b149205bd4a9e51490df501fa90f40a15f01dd93fb0e6073350c68cc6
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ef7c5a8852f372f03456eba3acdcf837798a16a3066b10d4a76362dcdf5c872
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a10cf0d903270d13b8f6dd0486ff41b10499ddfbf3f5e1b93ff46e9f7a70102
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba359f490230d80bb170385a2d7438d7ac91b791c81811431933971010fdd027
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9197096a8984ac294a322f7608c12d88a2c6aa8735e78f4d1bafa804a0929c3
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8469e7c7a11a55213a1b26ff1ff81e338fb7aabfef5a28d26b009e0f552e0a25
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07e3900ae1f5fc9b813b6d61eb6e2adf648dc219937ca2499c8f7494f602d43f
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06809e973763e16119eac4534e8c35055f95c29a781afbc0e2b173aec37f1acb
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/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:e9477232db152287c80188c601e99fa4c35135624f4a2860cee1e4bc01d09439
+size 430150469

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec36024d9f354a1187099011d21b91fdc03dcc748a4ff35ddfee5f5234e3747
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3340b60acf2dce215d60911e1d10dfe6bf5cb35ada16bd5035053c9b7304ece
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f4edf75aa816e3295d6d28efa6d58e1273ea6e9b224ce39ca5fd6d6475da8a3
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:430c46a07e49ae43b1b9766669e8eebaf3d786d08452613970bed4182a457819
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00652bfede69a7510bb61b3f6f5734b077e54fc2f75d17ac054f77b2b69bf156
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e657332bd40f454cdc19b64cafbcafc2147dbc2d262448504ce7991d24c4ec
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89876d4d8b907fc7c92fffaa7d37148978b3a8f187d26557fb84724e7864d3ae
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f1417169726a77a0dcc9391d87f07b01e230f640bc002a51dc6c86fbf696f01
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d228a913aae6242124b5d1e977c59987a6f2f8794be1048b69c85a205daa82de
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b337c29e09c04b3916bf592c0c0100431b62dd0e86c673b1be1b257dcd9344
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631319f3d95fe3c34a5bb92690042c8fb0238a323d4bff1fbad2881abc41951f
+size 430150469

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d57536d6b2bd36b39ddffa8f5a19d7906551db48cc6834e53a39a562021d659
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a1cfe5b04796f462952267e55510ecbe279c30af31b63781111c8fa374aaec
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6523180bd30da7e0a47b6757f0d34c4d098f7173e4454f7cd52be434aa713aaa
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7aa63328b40cf564f8da326cbf94dbdc8c4828ae22ad82f987b07c12e76b8fc
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4605eb9ea821f6d5de2034e4490f391111f99e5529aafdb25488bbdc486edcdc
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0308f4040ec2ae950eb2a8568d7344525c4d48475d0e97a46213047fb796b2cb
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0106d82fae0856b78eb44bc22e39392102de48689843f4d3e4c51892adb617d
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8469015ca7d192546b2dbc8a0ceefd64b7a3d497843eeebd1da7a0c9e9035f27
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a62a972526d89730d86c8cdc51ce0055816e533adf8d51642bc003941d8997a
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:380c3afbed633b2b7f4600bc5fd9600de2f77ca9f5713b50f6d143181f7417ed
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5484dc5808786305a2ab99712f043d210fe981f9de05381ec24a2bcfbff6d9e6
+size 430150469

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eecf9d92cd445ef1ef52a58712361bb0236e4f9204cc6960adec9dc501f50a6a
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00912cc19e445b1a215c06a5eab30e46be5ab2acf1507dca2aa4e2cd09a44af7
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9df9e869b8aa7e66ec1cae7233b3062a705ed7a00ccacaea1b9a9dc4cd88a74
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbf39df961241da8b81d3b1cbc92f24d933253957a0a3e3f7ede97a7891ff9d2
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:132db6007792d0377338ab42bcc59a1eb28a537274f0f3e95d66aa4778a56513
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adb68f8bd30cf8dc1ab1e5b4d071cd4839dfb039a37aeedcf86511a32b0aa777
+size 430150483

qwen3-1.7b-sft/checkpoint-6502/global_step6502/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c3ea7fcb8bfca29c6b317eed9ee74d98dbe83fcc916b6cd6523c7c251e87a1b
+size 430150483