初始化项目，由ModelHub XC社区提供模型

Model: israel/AfriqueQwen-14B-multiturn_1 Source: Original Platform
2026-05-13 06:26:36 +08:00
commit 739a4afc6f
37 changed files with 1887 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip 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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: McGill-NLP/AfriqueQwen-14B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: AfriqueQwen-14B-multiturn_1
+  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. -->
+
+# AfriqueQwen-14B-multiturn_1
+
+This model is a fine-tuned version of [McGill-NLP/AfriqueQwen-14B](https://huggingface.co/McGill-NLP/AfriqueQwen-14B) on the afri_multiturn_1 dataset.
+
+## 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.2.0
+- Pytorch 2.10.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2
--- a/all_results.json
+++ b/all_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 481722301939712.0,
+    "train_loss": 0.401988563902201,
+    "train_runtime": 92209.7944,
+    "train_samples_per_second": 2.973,
+    "train_steps_per_second": 0.372
+}
--- a/chat_template.jinja
+++ b/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 %}
--- a/checkpoint-34265/chat_template.jinja
+++ b/checkpoint-34265/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 %}
--- a/checkpoint-34265/config.json
+++ b/checkpoint-34265/config.json
@@ -0,0 +1,75 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17408,
+  "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",
+    "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": 40,
+  "model_type": "qwen3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/checkpoint-34265/generation_config.json
+++ b/checkpoint-34265/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "5.2.0"
+}
--- a/checkpoint-34265/global_step34265/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
+++ b/checkpoint-34265/global_step34265/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bd50d884195d5a02ea5f502a46785abfabd5b1cf47691bc32ccc118d9f4a97e
+size 44304931131
--- a/checkpoint-34265/global_step34265/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
+++ b/checkpoint-34265/global_step34265/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ccd58cb4194e2cf5cf6e1f0a50cbb3e468a2684f9038c240b2a1b3f03ce6e89
+size 44304931131
--- a/checkpoint-34265/global_step34265/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
+++ b/checkpoint-34265/global_step34265/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b3d5120bd406c8d013b1b00bfbdb667f1ab91aab4a38e481cb6c4dacb00f24
+size 44304931131
--- a/checkpoint-34265/global_step34265/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
+++ b/checkpoint-34265/global_step34265/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22ae7249ce9ebb4f522b9ae323e6e49485156009bdf4a90e9b05200f536fbc5a
+size 44304931131
--- a/checkpoint-34265/global_step34265/zero_pp_rank_0_mp_rank_00_model_states.pt
+++ b/checkpoint-34265/global_step34265/zero_pp_rank_0_mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1a3c69cfa37a40b0012e147f818a20bba4e813563dcb10517df264e6ac3fd6d
+size 225000
--- a/checkpoint-34265/global_step34265/zero_pp_rank_1_mp_rank_00_model_states.pt
+++ b/checkpoint-34265/global_step34265/zero_pp_rank_1_mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cffa6c83b5cded0b3b59efa268b1d445f3829531df00a4cdb7dea63ae97a23f
+size 225000
--- a/checkpoint-34265/global_step34265/zero_pp_rank_2_mp_rank_00_model_states.pt
+++ b/checkpoint-34265/global_step34265/zero_pp_rank_2_mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0552dc1cd3d4a9a9a2a347b48ee4bbc750221f4c507ef4097a4435b8648e4c2a
+size 225000
--- a/checkpoint-34265/global_step34265/zero_pp_rank_3_mp_rank_00_model_states.pt
+++ b/checkpoint-34265/global_step34265/zero_pp_rank_3_mp_rank_00_model_states.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac7747d1566dd8677b2c5c41dfa9db4108c7f06a37b76ea63f8e7e651f53763
+size 225000
--- a/checkpoint-34265/latest
+++ b/checkpoint-34265/latest
@@ -0,0 +1 @@
+global_step34265
--- a/checkpoint-34265/model.safetensors
+++ b/checkpoint-34265/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca62e96fb25ec28dd201b6314f4ce7ee390c52f386feb103ec06cd666f0fc22
+size 29536666272
--- a/checkpoint-34265/rng_state_0.pth
+++ b/checkpoint-34265/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d5f83aeb4b3f559bd28377336d47659b320e7f6ef2e5a723d284716278a151
+size 15429
--- a/checkpoint-34265/rng_state_1.pth
+++ b/checkpoint-34265/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2626437dcb133ffcf003ac89603f8cce07459b93a98d760cd9419e0d6a994067
+size 15429
--- a/checkpoint-34265/rng_state_2.pth
+++ b/checkpoint-34265/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae777e24d50cb7159634e1245f0697ba0fc64d5b26d535f2c80e411371a90b1c
+size 15429
--- a/checkpoint-34265/rng_state_3.pth
+++ b/checkpoint-34265/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc5a67564eebcfc961e8f1406a7418cc73497c2935a39af0232ef59f8153a6a
+size 15429
--- a/checkpoint-34265/scheduler.pt
+++ b/checkpoint-34265/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c94495b2fdaa190f2f28183e73d97cd217405437055caeb77964e4120313faee
+size 1465
--- a/checkpoint-34265/tokenizer.json
+++ b/checkpoint-34265/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650
--- a/checkpoint-34265/tokenizer_config.json
+++ b/checkpoint-34265/tokenizer_config.json
@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/checkpoint-34265/trainer_state.json
+++ b/checkpoint-34265/trainer_state.json
@@ -0,0 +1,272 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 34265,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1459321415541773,
+      "grad_norm": 3.8735740724697223,
+      "learning_rate": 2.915086081120514e-06,
+      "loss": 1.154789306640625,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2918642831083546,
+      "grad_norm": 3.513073777315236,
+      "learning_rate": 5.833090166326233e-06,
+      "loss": 0.9386199340820313,
+      "step": 2000
+    },
+    {
+      "epoch": 0.43779642466253194,
+      "grad_norm": 2.667804789171682,
+      "learning_rate": 8.751094251531953e-06,
+      "loss": 0.8885218505859375,
+      "step": 3000
+    },
+    {
+      "epoch": 0.5837285662167092,
+      "grad_norm": 1.8311641416860456,
+      "learning_rate": 9.991513345767592e-06,
+      "loss": 0.8694163208007812,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7296607077708865,
+      "grad_norm": 2.250397237666049,
+      "learning_rate": 9.936020028278053e-06,
+      "loss": 0.85284765625,
+      "step": 5000
+    },
+    {
+      "epoch": 0.8755928493250639,
+      "grad_norm": 2.6756387164181197,
+      "learning_rate": 9.829343371836088e-06,
+      "loss": 0.821312744140625,
+      "step": 6000
+    },
+    {
+      "epoch": 1.021452024808464,
+      "grad_norm": 2.6729990910245593,
+      "learning_rate": 9.672589544454328e-06,
+      "loss": 0.7774617919921875,
+      "step": 7000
+    },
+    {
+      "epoch": 1.1673841663626414,
+      "grad_norm": 2.642277321184833,
+      "learning_rate": 9.46738398205746e-06,
+      "loss": 0.608907958984375,
+      "step": 8000
+    },
+    {
+      "epoch": 1.3133163079168186,
+      "grad_norm": 2.1544218289818913,
+      "learning_rate": 9.215854533761766e-06,
+      "loss": 0.6088528442382812,
+      "step": 9000
+    },
+    {
+      "epoch": 1.459248449470996,
+      "grad_norm": 2.3990917619771497,
+      "learning_rate": 8.920609397454381e-06,
+      "loss": 0.6051533203125,
+      "step": 10000
+    },
+    {
+      "epoch": 1.6051805910251733,
+      "grad_norm": 2.5614175915079387,
+      "learning_rate": 8.584710074466158e-06,
+      "loss": 0.6031138916015625,
+      "step": 11000
+    },
+    {
+      "epoch": 1.7511127325793505,
+      "grad_norm": 1.5472599757402412,
+      "learning_rate": 8.211639623780629e-06,
+      "loss": 0.6085886840820313,
+      "step": 12000
+    },
+    {
+      "epoch": 1.897044874133528,
+      "grad_norm": 2.384688518854998,
+      "learning_rate": 7.805266544962458e-06,
+      "loss": 0.6080531616210938,
+      "step": 13000
+    },
+    {
+      "epoch": 2.042904049616928,
+      "grad_norm": 2.0076063347622974,
+      "learning_rate": 7.3698046643160645e-06,
+      "loss": 0.520530029296875,
+      "step": 14000
+    },
+    {
+      "epoch": 2.1888361911711054,
+      "grad_norm": 1.529742164922155,
+      "learning_rate": 6.909769440229038e-06,
+      "loss": 0.33792144775390626,
+      "step": 15000
+    },
+    {
+      "epoch": 2.334768332725283,
+      "grad_norm": 2.116689548920815,
+      "learning_rate": 6.4299311407857035e-06,
+      "loss": 0.3347291259765625,
+      "step": 16000
+    },
+    {
+      "epoch": 2.48070047427946,
+      "grad_norm": 1.8084278631560584,
+      "learning_rate": 5.935265379168761e-06,
+      "loss": 0.3385657958984375,
+      "step": 17000
+    },
+    {
+      "epoch": 2.6266326158336373,
+      "grad_norm": 3.29945063597593,
+      "learning_rate": 5.430901519764892e-06,
+      "loss": 0.33349261474609376,
+      "step": 18000
+    },
+    {
+      "epoch": 2.7725647573878147,
+      "grad_norm": 1.9290178050582503,
+      "learning_rate": 4.9220694899697185e-06,
+      "loss": 0.3383995361328125,
+      "step": 19000
+    },
+    {
+      "epoch": 2.918496898941992,
+      "grad_norm": 1.8157318709036212,
+      "learning_rate": 4.414045549219315e-06,
+      "loss": 0.3316441650390625,
+      "step": 20000
+    },
+    {
+      "epoch": 3.064356074425392,
+      "grad_norm": 3.0277622115117175,
+      "learning_rate": 3.912097577588397e-06,
+      "loss": 0.2421361541748047,
+      "step": 21000
+    },
+    {
+      "epoch": 3.2102882159795696,
+      "grad_norm": 2.0816758739547914,
+      "learning_rate": 3.4214304512770823e-06,
+      "loss": 0.1313203887939453,
+      "step": 22000
+    },
+    {
+      "epoch": 3.356220357533747,
+      "grad_norm": 1.739691217957409,
+      "learning_rate": 2.9471320714071095e-06,
+      "loss": 0.12995486450195312,
+      "step": 23000
+    },
+    {
+      "epoch": 3.502152499087924,
+      "grad_norm": 3.1257187709887875,
+      "learning_rate": 2.4941206057740675e-06,
+      "loss": 0.1304095458984375,
+      "step": 24000
+    },
+    {
+      "epoch": 3.6480846406421015,
+      "grad_norm": 2.2140995652592785,
+      "learning_rate": 2.06709349062457e-06,
+      "loss": 0.12645170593261718,
+      "step": 25000
+    },
+    {
+      "epoch": 3.7940167821962785,
+      "grad_norm": 1.7680132762507759,
+      "learning_rate": 1.6704787212769829e-06,
+      "loss": 0.12362543487548829,
+      "step": 26000
+    },
+    {
+      "epoch": 3.939948923750456,
+      "grad_norm": 3.186667247027872,
+      "learning_rate": 1.3083889366705216e-06,
+      "loss": 0.11934644317626954,
+      "step": 27000
+    },
+    {
+      "epoch": 4.085808099233856,
+      "grad_norm": 0.9381402976600279,
+      "learning_rate": 9.845787739562829e-07,
+      "loss": 0.07250856018066407,
+      "step": 28000
+    },
+    {
+      "epoch": 4.231740240788033,
+      "grad_norm": 1.5081719675375433,
+      "learning_rate": 7.024059353355333e-07,
+      "loss": 0.03657876205444336,
+      "step": 29000
+    },
+    {
+      "epoch": 4.377672382342211,
+      "grad_norm": 1.3793894154463466,
+      "learning_rate": 4.64796370857008e-07,
+      "loss": 0.035053966522216796,
+      "step": 30000
+    },
+    {
+      "epoch": 4.523604523896388,
+      "grad_norm": 1.9377667427717677,
+      "learning_rate": 2.7421393820510846e-07,
+      "loss": 0.0349309196472168,
+      "step": 31000
+    },
+    {
+      "epoch": 4.669536665450566,
+      "grad_norm": 1.109997862535006,
+      "learning_rate": 1.326348540874095e-07,
+      "loss": 0.03447756195068359,
+      "step": 32000
+    },
+    {
+      "epoch": 4.815468807004743,
+      "grad_norm": 1.152236730081828,
+      "learning_rate": 4.152720214406214e-08,
+      "loss": 0.03444968414306641,
+      "step": 33000
+    },
+    {
+      "epoch": 4.96140094855892,
+      "grad_norm": 1.6457557752833996,
+      "learning_rate": 1.8357098688476238e-09,
+      "loss": 0.034835365295410155,
+      "step": 34000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 34265,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 50000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 481722301939712.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/checkpoint-34265/training_args.bin
+++ b/checkpoint-34265/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeba44e7611f40dbc5cb19262d1f7cf185351624bc850381dceb5317d44a57f4
+size 7377
--- a/checkpoint-34265/zero_to_fp32.py
+++ b/checkpoint-34265/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 ZERO_STAGE not 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("Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info("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)
--- a/config.json
+++ b/config.json
@@ -0,0 +1,75 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17408,
+  "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",
+    "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": 40,
+  "model_type": "qwen3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "5.2.0"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca62e96fb25ec28dd201b6314f4ce7ee390c52f386feb103ec06cd666f0fc22
+size 29536666272
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 481722301939712.0,
+    "train_loss": 0.401988563902201,
+    "train_runtime": 92209.7944,
+    "train_samples_per_second": 2.973,
+    "train_steps_per_second": 0.372
+}
--- a/trainer_log.jsonl
+++ b/trainer_log.jsonl
@@ -0,0 +1,35 @@
+{"current_steps": 1000, "total_steps": 34265, "loss": 1.154789306640625, "lr": 2.915086081120514e-06, "epoch": 0.1459321415541773, "percentage": 2.92, "elapsed_time": "0:44:56", "remaining_time": "1 day, 0:55:14"}
+{"current_steps": 2000, "total_steps": 34265, "loss": 0.9386199340820313, "lr": 5.833090166326233e-06, "epoch": 0.2918642831083546, "percentage": 5.84, "elapsed_time": "1:30:05", "remaining_time": "1 day, 0:13:21"}
+{"current_steps": 3000, "total_steps": 34265, "loss": 0.8885218505859375, "lr": 8.751094251531953e-06, "epoch": 0.43779642466253194, "percentage": 8.76, "elapsed_time": "2:14:43", "remaining_time": "23:24:07"}
+{"current_steps": 4000, "total_steps": 34265, "loss": 0.8694163208007812, "lr": 9.991513345767592e-06, "epoch": 0.5837285662167092, "percentage": 11.67, "elapsed_time": "2:59:17", "remaining_time": "22:36:31"}
+{"current_steps": 5000, "total_steps": 34265, "loss": 0.85284765625, "lr": 9.936020028278053e-06, "epoch": 0.7296607077708865, "percentage": 14.59, "elapsed_time": "3:44:00", "remaining_time": "21:51:05"}
+{"current_steps": 6000, "total_steps": 34265, "loss": 0.821312744140625, "lr": 9.829343371836088e-06, "epoch": 0.8755928493250639, "percentage": 17.51, "elapsed_time": "4:28:31", "remaining_time": "21:04:59"}
+{"current_steps": 7000, "total_steps": 34265, "loss": 0.7774617919921875, "lr": 9.672589544454328e-06, "epoch": 1.021452024808464, "percentage": 20.43, "elapsed_time": "5:13:07", "remaining_time": "20:19:38"}
+{"current_steps": 8000, "total_steps": 34265, "loss": 0.608907958984375, "lr": 9.46738398205746e-06, "epoch": 1.1673841663626414, "percentage": 23.35, "elapsed_time": "5:57:43", "remaining_time": "19:34:26"}
+{"current_steps": 9000, "total_steps": 34265, "loss": 0.6088528442382812, "lr": 9.215854533761766e-06, "epoch": 1.3133163079168186, "percentage": 26.27, "elapsed_time": "6:42:28", "remaining_time": "18:49:49"}
+{"current_steps": 10000, "total_steps": 34265, "loss": 0.6051533203125, "lr": 8.920609397454381e-06, "epoch": 1.459248449470996, "percentage": 29.18, "elapsed_time": "7:27:22", "remaining_time": "18:05:33"}
+{"current_steps": 11000, "total_steps": 34265, "loss": 0.6031138916015625, "lr": 8.584710074466158e-06, "epoch": 1.6051805910251733, "percentage": 32.1, "elapsed_time": "8:12:16", "remaining_time": "17:21:10"}
+{"current_steps": 12000, "total_steps": 34265, "loss": 0.6085886840820313, "lr": 8.211639623780629e-06, "epoch": 1.7511127325793505, "percentage": 35.02, "elapsed_time": "8:57:00", "remaining_time": "16:36:21"}
+{"current_steps": 13000, "total_steps": 34265, "loss": 0.6080531616210938, "lr": 7.805266544962458e-06, "epoch": 1.897044874133528, "percentage": 37.94, "elapsed_time": "9:41:39", "remaining_time": "15:51:27"}
+{"current_steps": 14000, "total_steps": 34265, "loss": 0.520530029296875, "lr": 7.3698046643160645e-06, "epoch": 2.042904049616928, "percentage": 40.86, "elapsed_time": "10:26:21", "remaining_time": "15:06:39"}
+{"current_steps": 15000, "total_steps": 34265, "loss": 0.33792144775390626, "lr": 6.909769440229038e-06, "epoch": 2.1888361911711054, "percentage": 43.78, "elapsed_time": "11:10:38", "remaining_time": "14:21:19"}
+{"current_steps": 16000, "total_steps": 34265, "loss": 0.3347291259765625, "lr": 6.4299311407857035e-06, "epoch": 2.334768332725283, "percentage": 46.69, "elapsed_time": "11:55:04", "remaining_time": "13:36:17"}
+{"current_steps": 17000, "total_steps": 34265, "loss": 0.3385657958984375, "lr": 5.935265379168761e-06, "epoch": 2.48070047427946, "percentage": 49.61, "elapsed_time": "12:39:52", "remaining_time": "12:51:43"}
+{"current_steps": 18000, "total_steps": 34265, "loss": 0.33349261474609376, "lr": 5.430901519764892e-06, "epoch": 2.6266326158336373, "percentage": 52.53, "elapsed_time": "13:24:42", "remaining_time": "12:07:08"}
+{"current_steps": 19000, "total_steps": 34265, "loss": 0.3383995361328125, "lr": 4.9220694899697185e-06, "epoch": 2.7725647573878147, "percentage": 55.45, "elapsed_time": "14:09:29", "remaining_time": "11:22:29"}
+{"current_steps": 20000, "total_steps": 34265, "loss": 0.3316441650390625, "lr": 4.414045549219315e-06, "epoch": 2.918496898941992, "percentage": 58.37, "elapsed_time": "14:53:49", "remaining_time": "10:37:31"}
+{"current_steps": 21000, "total_steps": 34265, "loss": 0.2421361541748047, "lr": 3.912097577588397e-06, "epoch": 3.064356074425392, "percentage": 61.29, "elapsed_time": "15:38:36", "remaining_time": "9:52:53"}
+{"current_steps": 22000, "total_steps": 34265, "loss": 0.1313203887939453, "lr": 3.4214304512770823e-06, "epoch": 3.2102882159795696, "percentage": 64.21, "elapsed_time": "16:23:17", "remaining_time": "9:08:11"}
+{"current_steps": 23000, "total_steps": 34265, "loss": 0.12995486450195312, "lr": 2.9471320714071095e-06, "epoch": 3.356220357533747, "percentage": 67.12, "elapsed_time": "17:08:01", "remaining_time": "8:23:30"}
+{"current_steps": 24000, "total_steps": 34265, "loss": 0.1304095458984375, "lr": 2.4941206057740675e-06, "epoch": 3.502152499087924, "percentage": 70.04, "elapsed_time": "17:52:36", "remaining_time": "7:38:45"}
+{"current_steps": 25000, "total_steps": 34265, "loss": 0.12645170593261718, "lr": 2.06709349062457e-06, "epoch": 3.6480846406421015, "percentage": 72.96, "elapsed_time": "18:37:12", "remaining_time": "6:54:02"}
+{"current_steps": 26000, "total_steps": 34265, "loss": 0.12362543487548829, "lr": 1.6704787212769829e-06, "epoch": 3.7940167821962785, "percentage": 75.88, "elapsed_time": "19:21:44", "remaining_time": "6:09:17"}
+{"current_steps": 27000, "total_steps": 34265, "loss": 0.11934644317626954, "lr": 1.3083889366705216e-06, "epoch": 3.939948923750456, "percentage": 78.8, "elapsed_time": "20:06:33", "remaining_time": "5:24:39"}
+{"current_steps": 28000, "total_steps": 34265, "loss": 0.07250856018066407, "lr": 9.845787739562829e-07, "epoch": 4.085808099233856, "percentage": 81.72, "elapsed_time": "20:51:17", "remaining_time": "4:39:58"}
+{"current_steps": 29000, "total_steps": 34265, "loss": 0.03657876205444336, "lr": 7.024059353355333e-07, "epoch": 4.231740240788033, "percentage": 84.63, "elapsed_time": "21:35:41", "remaining_time": "3:55:14"}
+{"current_steps": 30000, "total_steps": 34265, "loss": 0.035053966522216796, "lr": 4.64796370857008e-07, "epoch": 4.377672382342211, "percentage": 87.55, "elapsed_time": "22:20:07", "remaining_time": "3:10:31"}
+{"current_steps": 31000, "total_steps": 34265, "loss": 0.0349309196472168, "lr": 2.7421393820510846e-07, "epoch": 4.523604523896388, "percentage": 90.47, "elapsed_time": "23:04:46", "remaining_time": "2:25:50"}
+{"current_steps": 32000, "total_steps": 34265, "loss": 0.03447756195068359, "lr": 1.326348540874095e-07, "epoch": 4.669536665450566, "percentage": 93.39, "elapsed_time": "23:49:25", "remaining_time": "1:41:10"}
+{"current_steps": 33000, "total_steps": 34265, "loss": 0.03444968414306641, "lr": 4.152720214406214e-08, "epoch": 4.815468807004743, "percentage": 96.31, "elapsed_time": "1 day, 0:34:23", "remaining_time": "0:56:31"}
+{"current_steps": 34000, "total_steps": 34265, "loss": 0.034835365295410155, "lr": 1.8357098688476238e-09, "epoch": 4.96140094855892, "percentage": 99.23, "elapsed_time": "1 day, 1:19:16", "remaining_time": "0:11:50"}
+{"current_steps": 34265, "total_steps": 34265, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1 day, 1:36:49", "remaining_time": "0:00:00"}
--- a/trainer_state.json
+++ b/trainer_state.json
@@ -0,0 +1,281 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 34265,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1459321415541773,
+      "grad_norm": 3.8735740724697223,
+      "learning_rate": 2.915086081120514e-06,
+      "loss": 1.154789306640625,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2918642831083546,
+      "grad_norm": 3.513073777315236,
+      "learning_rate": 5.833090166326233e-06,
+      "loss": 0.9386199340820313,
+      "step": 2000
+    },
+    {
+      "epoch": 0.43779642466253194,
+      "grad_norm": 2.667804789171682,
+      "learning_rate": 8.751094251531953e-06,
+      "loss": 0.8885218505859375,
+      "step": 3000
+    },
+    {
+      "epoch": 0.5837285662167092,
+      "grad_norm": 1.8311641416860456,
+      "learning_rate": 9.991513345767592e-06,
+      "loss": 0.8694163208007812,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7296607077708865,
+      "grad_norm": 2.250397237666049,
+      "learning_rate": 9.936020028278053e-06,
+      "loss": 0.85284765625,
+      "step": 5000
+    },
+    {
+      "epoch": 0.8755928493250639,
+      "grad_norm": 2.6756387164181197,
+      "learning_rate": 9.829343371836088e-06,
+      "loss": 0.821312744140625,
+      "step": 6000
+    },
+    {
+      "epoch": 1.021452024808464,
+      "grad_norm": 2.6729990910245593,
+      "learning_rate": 9.672589544454328e-06,
+      "loss": 0.7774617919921875,
+      "step": 7000
+    },
+    {
+      "epoch": 1.1673841663626414,
+      "grad_norm": 2.642277321184833,
+      "learning_rate": 9.46738398205746e-06,
+      "loss": 0.608907958984375,
+      "step": 8000
+    },
+    {
+      "epoch": 1.3133163079168186,
+      "grad_norm": 2.1544218289818913,
+      "learning_rate": 9.215854533761766e-06,
+      "loss": 0.6088528442382812,
+      "step": 9000
+    },
+    {
+      "epoch": 1.459248449470996,
+      "grad_norm": 2.3990917619771497,
+      "learning_rate": 8.920609397454381e-06,
+      "loss": 0.6051533203125,
+      "step": 10000
+    },
+    {
+      "epoch": 1.6051805910251733,
+      "grad_norm": 2.5614175915079387,
+      "learning_rate": 8.584710074466158e-06,
+      "loss": 0.6031138916015625,
+      "step": 11000
+    },
+    {
+      "epoch": 1.7511127325793505,
+      "grad_norm": 1.5472599757402412,
+      "learning_rate": 8.211639623780629e-06,
+      "loss": 0.6085886840820313,
+      "step": 12000
+    },
+    {
+      "epoch": 1.897044874133528,
+      "grad_norm": 2.384688518854998,
+      "learning_rate": 7.805266544962458e-06,
+      "loss": 0.6080531616210938,
+      "step": 13000
+    },
+    {
+      "epoch": 2.042904049616928,
+      "grad_norm": 2.0076063347622974,
+      "learning_rate": 7.3698046643160645e-06,
+      "loss": 0.520530029296875,
+      "step": 14000
+    },
+    {
+      "epoch": 2.1888361911711054,
+      "grad_norm": 1.529742164922155,
+      "learning_rate": 6.909769440229038e-06,
+      "loss": 0.33792144775390626,
+      "step": 15000
+    },
+    {
+      "epoch": 2.334768332725283,
+      "grad_norm": 2.116689548920815,
+      "learning_rate": 6.4299311407857035e-06,
+      "loss": 0.3347291259765625,
+      "step": 16000
+    },
+    {
+      "epoch": 2.48070047427946,
+      "grad_norm": 1.8084278631560584,
+      "learning_rate": 5.935265379168761e-06,
+      "loss": 0.3385657958984375,
+      "step": 17000
+    },
+    {
+      "epoch": 2.6266326158336373,
+      "grad_norm": 3.29945063597593,
+      "learning_rate": 5.430901519764892e-06,
+      "loss": 0.33349261474609376,
+      "step": 18000
+    },
+    {
+      "epoch": 2.7725647573878147,
+      "grad_norm": 1.9290178050582503,
+      "learning_rate": 4.9220694899697185e-06,
+      "loss": 0.3383995361328125,
+      "step": 19000
+    },
+    {
+      "epoch": 2.918496898941992,
+      "grad_norm": 1.8157318709036212,
+      "learning_rate": 4.414045549219315e-06,
+      "loss": 0.3316441650390625,
+      "step": 20000
+    },
+    {
+      "epoch": 3.064356074425392,
+      "grad_norm": 3.0277622115117175,
+      "learning_rate": 3.912097577588397e-06,
+      "loss": 0.2421361541748047,
+      "step": 21000
+    },
+    {
+      "epoch": 3.2102882159795696,
+      "grad_norm": 2.0816758739547914,
+      "learning_rate": 3.4214304512770823e-06,
+      "loss": 0.1313203887939453,
+      "step": 22000
+    },
+    {
+      "epoch": 3.356220357533747,
+      "grad_norm": 1.739691217957409,
+      "learning_rate": 2.9471320714071095e-06,
+      "loss": 0.12995486450195312,
+      "step": 23000
+    },
+    {
+      "epoch": 3.502152499087924,
+      "grad_norm": 3.1257187709887875,
+      "learning_rate": 2.4941206057740675e-06,
+      "loss": 0.1304095458984375,
+      "step": 24000
+    },
+    {
+      "epoch": 3.6480846406421015,
+      "grad_norm": 2.2140995652592785,
+      "learning_rate": 2.06709349062457e-06,
+      "loss": 0.12645170593261718,
+      "step": 25000
+    },
+    {
+      "epoch": 3.7940167821962785,
+      "grad_norm": 1.7680132762507759,
+      "learning_rate": 1.6704787212769829e-06,
+      "loss": 0.12362543487548829,
+      "step": 26000
+    },
+    {
+      "epoch": 3.939948923750456,
+      "grad_norm": 3.186667247027872,
+      "learning_rate": 1.3083889366705216e-06,
+      "loss": 0.11934644317626954,
+      "step": 27000
+    },
+    {
+      "epoch": 4.085808099233856,
+      "grad_norm": 0.9381402976600279,
+      "learning_rate": 9.845787739562829e-07,
+      "loss": 0.07250856018066407,
+      "step": 28000
+    },
+    {
+      "epoch": 4.231740240788033,
+      "grad_norm": 1.5081719675375433,
+      "learning_rate": 7.024059353355333e-07,
+      "loss": 0.03657876205444336,
+      "step": 29000
+    },
+    {
+      "epoch": 4.377672382342211,
+      "grad_norm": 1.3793894154463466,
+      "learning_rate": 4.64796370857008e-07,
+      "loss": 0.035053966522216796,
+      "step": 30000
+    },
+    {
+      "epoch": 4.523604523896388,
+      "grad_norm": 1.9377667427717677,
+      "learning_rate": 2.7421393820510846e-07,
+      "loss": 0.0349309196472168,
+      "step": 31000
+    },
+    {
+      "epoch": 4.669536665450566,
+      "grad_norm": 1.109997862535006,
+      "learning_rate": 1.326348540874095e-07,
+      "loss": 0.03447756195068359,
+      "step": 32000
+    },
+    {
+      "epoch": 4.815468807004743,
+      "grad_norm": 1.152236730081828,
+      "learning_rate": 4.152720214406214e-08,
+      "loss": 0.03444968414306641,
+      "step": 33000
+    },
+    {
+      "epoch": 4.96140094855892,
+      "grad_norm": 1.6457557752833996,
+      "learning_rate": 1.8357098688476238e-09,
+      "loss": 0.034835365295410155,
+      "step": 34000
+    },
+    {
+      "epoch": 5.0,
+      "step": 34265,
+      "total_flos": 481722301939712.0,
+      "train_loss": 0.401988563902201,
+      "train_runtime": 92209.7944,
+      "train_samples_per_second": 2.973,
+      "train_steps_per_second": 0.372
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 34265,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 50000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 481722301939712.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeba44e7611f40dbc5cb19262d1f7cf185351624bc850381dceb5317d44a57f4
+size 7377
--- a/training_loss.png
+++ b/training_loss.png