Upload folder using huggingface_hub

.gitattributes

@@ -44,3 +44,4 @@ osgenesis-llama/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 agenttrek-llama/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 webrl-llama/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 atomic_expert/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+test_admin/tokenizer.json filter=lfs diff=lfs merge=lfs -text

test_admin/README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: admin
+  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. -->
+
+# admin
+
+This model is a fine-tuned version of [/ceph/home/muhan01/huggingfacemodels/Qwen2.5-7B-Instruct](https://huggingface.co//ceph/home/muhan01/huggingfacemodels/Qwen2.5-7B-Instruct) on the test_admin dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1588
+
+## 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: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 7
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 28
+- total_eval_batch_size: 7
+- optimizer: Use 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: 0.1
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.2217        | 0.7569 | 200  | 0.2220          |
+| 0.1209        | 1.5109 | 400  | 0.1692          |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.2-rc0

test_admin/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

test_admin/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.158763587474823,
+    "eval_runtime": 94.1747,
+    "eval_samples_per_second": 8.739,
+    "eval_steps_per_second": 1.253,
+    "total_flos": 71607640850432.0,
+    "train_loss": 0.2318565127984533,
+    "train_runtime": 10363.9156,
+    "train_samples_per_second": 1.428,
+    "train_steps_per_second": 0.051
+}

test_admin/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

test_admin/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

test_admin/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.158763587474823,
+    "eval_runtime": 94.1747,
+    "eval_samples_per_second": 8.739,
+    "eval_steps_per_second": 1.253
+}

test_admin/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.1"
+}

test_admin/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:304351c356b82b41bb0c4d31fbb79d6cd768e77aa3c4cdda67ebdea13903ce06
+size 4877660776

test_admin/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8fb21b95160ebaf7d83c3abc74592b9080dc3cb7b74134c0bfb55b0c60b2262
+size 4932751008

test_admin/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9dee4d4fea16853a7a648e4a16f62c7e3f8a77e36dcf63e29e51f54bac44f20
+size 4330865200

test_admin/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00c11a9336570103c0685441f6fd4262bd55d6cd7acbe4938f8fcd812572957
+size 1089994880

test_admin/model.safetensors.index.json

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

test_admin/runs/Jan07_02-17-43_hgx004/events.out.tfevents.1767723629.hgx004

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5716f8047d3165d30c26ae9fe81358d108a526f4f81378f00b22c97a68a09704
+size 18110

test_admin/runs/Jan07_02-17-43_hgx004/events.out.tfevents.1767734113.hgx004

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ae49f689bc2099f6bcbb12e03d2a1f9e22f653641bd90bb71432875ef70987
+size 311

test_admin/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

test_admin/tokenizer.json

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

test_admin/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

test_admin/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 71607640850432.0,
+    "train_loss": 0.2318565127984533,
+    "train_runtime": 10363.9156,
+    "train_samples_per_second": 1.428,
+    "train_steps_per_second": 0.051
+}

test_admin/trainer_log.jsonl

@@ -0,0 +1,56 @@
+{"current_steps": 10, "total_steps": 530, "loss": 1.4503, "lr": 1.6981132075471698e-06, "epoch": 0.03784295175023652, "percentage": 1.89, "elapsed_time": "0:03:21", "remaining_time": "2:54:41"}
+{"current_steps": 20, "total_steps": 530, "loss": 0.8761, "lr": 3.5849056603773586e-06, "epoch": 0.07568590350047304, "percentage": 3.77, "elapsed_time": "0:06:34", "remaining_time": "2:47:33"}
+{"current_steps": 30, "total_steps": 530, "loss": 0.5782, "lr": 5.4716981132075475e-06, "epoch": 0.11352885525070956, "percentage": 5.66, "elapsed_time": "0:09:45", "remaining_time": "2:42:34"}
+{"current_steps": 40, "total_steps": 530, "loss": 0.4365, "lr": 7.358490566037736e-06, "epoch": 0.15137180700094607, "percentage": 7.55, "elapsed_time": "0:12:53", "remaining_time": "2:37:59"}
+{"current_steps": 50, "total_steps": 530, "loss": 0.3779, "lr": 9.245283018867926e-06, "epoch": 0.1892147587511826, "percentage": 9.43, "elapsed_time": "0:16:04", "remaining_time": "2:34:15"}
+{"current_steps": 60, "total_steps": 530, "loss": 0.3345, "lr": 9.99609654676786e-06, "epoch": 0.22705771050141912, "percentage": 11.32, "elapsed_time": "0:19:11", "remaining_time": "2:30:23"}
+{"current_steps": 70, "total_steps": 530, "loss": 0.3279, "lr": 9.9722641784023e-06, "epoch": 0.26490066225165565, "percentage": 13.21, "elapsed_time": "0:22:20", "remaining_time": "2:26:48"}
+{"current_steps": 80, "total_steps": 530, "loss": 0.3057, "lr": 9.92687124249773e-06, "epoch": 0.30274361400189215, "percentage": 15.09, "elapsed_time": "0:25:37", "remaining_time": "2:24:09"}
+{"current_steps": 90, "total_steps": 530, "loss": 0.2971, "lr": 9.860114570402055e-06, "epoch": 0.34058656575212864, "percentage": 16.98, "elapsed_time": "0:28:46", "remaining_time": "2:20:39"}
+{"current_steps": 100, "total_steps": 530, "loss": 0.2811, "lr": 9.772283630189727e-06, "epoch": 0.3784295175023652, "percentage": 18.87, "elapsed_time": "0:31:57", "remaining_time": "2:17:23"}
+{"current_steps": 110, "total_steps": 530, "loss": 0.2664, "lr": 9.663759271479858e-06, "epoch": 0.4162724692526017, "percentage": 20.75, "elapsed_time": "0:35:04", "remaining_time": "2:13:54"}
+{"current_steps": 120, "total_steps": 530, "loss": 0.2721, "lr": 9.535012074008688e-06, "epoch": 0.45411542100283825, "percentage": 22.64, "elapsed_time": "0:38:17", "remaining_time": "2:10:49"}
+{"current_steps": 130, "total_steps": 530, "loss": 0.2549, "lr": 9.386600307117293e-06, "epoch": 0.49195837275307475, "percentage": 24.53, "elapsed_time": "0:41:32", "remaining_time": "2:07:48"}
+{"current_steps": 140, "total_steps": 530, "loss": 0.2534, "lr": 9.219167509002526e-06, "epoch": 0.5298013245033113, "percentage": 26.42, "elapsed_time": "0:44:39", "remaining_time": "2:04:25"}
+{"current_steps": 150, "total_steps": 530, "loss": 0.2447, "lr": 9.033439696227966e-06, "epoch": 0.5676442762535477, "percentage": 28.3, "elapsed_time": "0:47:49", "remaining_time": "2:01:08"}
+{"current_steps": 160, "total_steps": 530, "loss": 0.2491, "lr": 8.83022221559489e-06, "epoch": 0.6054872280037843, "percentage": 30.19, "elapsed_time": "0:51:00", "remaining_time": "1:57:56"}
+{"current_steps": 170, "total_steps": 530, "loss": 0.2397, "lr": 8.610396252024113e-06, "epoch": 0.6433301797540208, "percentage": 32.08, "elapsed_time": "0:54:07", "remaining_time": "1:54:37"}
+{"current_steps": 180, "total_steps": 530, "loss": 0.2172, "lr": 8.374915007591053e-06, "epoch": 0.6811731315042573, "percentage": 33.96, "elapsed_time": "0:57:19", "remaining_time": "1:51:27"}
+{"current_steps": 190, "total_steps": 530, "loss": 0.234, "lr": 8.124799568282418e-06, "epoch": 0.7190160832544938, "percentage": 35.85, "elapsed_time": "1:00:26", "remaining_time": "1:48:09"}
+{"current_steps": 200, "total_steps": 530, "loss": 0.2217, "lr": 7.861134476396903e-06, "epoch": 0.7568590350047304, "percentage": 37.74, "elapsed_time": "1:03:41", "remaining_time": "1:45:05"}
+{"current_steps": 200, "total_steps": 530, "eval_loss": 0.2220437228679657, "epoch": 0.7568590350047304, "percentage": 37.74, "elapsed_time": "1:05:14", "remaining_time": "1:47:39"}
+{"current_steps": 210, "total_steps": 530, "loss": 0.2129, "lr": 7.58506302778873e-06, "epoch": 0.7947019867549668, "percentage": 39.62, "elapsed_time": "1:08:27", "remaining_time": "1:44:18"}
+{"current_steps": 220, "total_steps": 530, "loss": 0.2146, "lr": 7.297782314345972e-06, "epoch": 0.8325449385052034, "percentage": 41.51, "elapsed_time": "1:11:39", "remaining_time": "1:40:57"}
+{"current_steps": 230, "total_steps": 530, "loss": 0.1948, "lr": 7.00053803320028e-06, "epoch": 0.8703878902554399, "percentage": 43.4, "elapsed_time": "1:14:54", "remaining_time": "1:37:41"}
+{"current_steps": 240, "total_steps": 530, "loss": 0.2056, "lr": 6.694619085176159e-06, "epoch": 0.9082308420056765, "percentage": 45.28, "elapsed_time": "1:17:58", "remaining_time": "1:34:13"}
+{"current_steps": 250, "total_steps": 530, "loss": 0.1986, "lr": 6.381351985901842e-06, "epoch": 0.9460737937559129, "percentage": 47.17, "elapsed_time": "1:21:08", "remaining_time": "1:30:52"}
+{"current_steps": 260, "total_steps": 530, "loss": 0.1962, "lr": 6.062095113816069e-06, "epoch": 0.9839167455061495, "percentage": 49.06, "elapsed_time": "1:24:22", "remaining_time": "1:27:37"}
+{"current_steps": 270, "total_steps": 530, "loss": 0.1666, "lr": 5.738232820012407e-06, "epoch": 1.0189214758751182, "percentage": 50.94, "elapsed_time": "1:27:46", "remaining_time": "1:24:31"}
+{"current_steps": 280, "total_steps": 530, "loss": 0.1459, "lr": 5.411169425461822e-06, "epoch": 1.0567644276253547, "percentage": 52.83, "elapsed_time": "1:30:59", "remaining_time": "1:21:14"}
+{"current_steps": 290, "total_steps": 530, "loss": 0.1453, "lr": 5.082323131642496e-06, "epoch": 1.0946073793755913, "percentage": 54.72, "elapsed_time": "1:34:12", "remaining_time": "1:17:58"}
+{"current_steps": 300, "total_steps": 530, "loss": 0.1401, "lr": 4.753119870981486e-06, "epoch": 1.1324503311258278, "percentage": 56.6, "elapsed_time": "1:37:22", "remaining_time": "1:14:39"}
+{"current_steps": 310, "total_steps": 530, "loss": 0.132, "lr": 4.424987123773654e-06, "epoch": 1.1702932828760644, "percentage": 58.49, "elapsed_time": "1:40:27", "remaining_time": "1:11:17"}
+{"current_steps": 320, "total_steps": 530, "loss": 0.1342, "lr": 4.0993477283888264e-06, "epoch": 1.208136234626301, "percentage": 60.38, "elapsed_time": "1:43:39", "remaining_time": "1:08:01"}
+{"current_steps": 330, "total_steps": 530, "loss": 0.1322, "lr": 3.777613711607087e-06, "epoch": 1.2459791863765375, "percentage": 62.26, "elapsed_time": "1:46:51", "remaining_time": "1:04:46"}
+{"current_steps": 340, "total_steps": 530, "loss": 0.1368, "lr": 3.46118016583494e-06, "epoch": 1.2838221381267738, "percentage": 64.15, "elapsed_time": "1:50:05", "remaining_time": "1:01:31"}
+{"current_steps": 350, "total_steps": 530, "loss": 0.1301, "lr": 3.1514191997517387e-06, "epoch": 1.3216650898770104, "percentage": 66.04, "elapsed_time": "1:53:17", "remaining_time": "0:58:16"}
+{"current_steps": 360, "total_steps": 530, "loss": 0.1314, "lr": 2.8496739886173994e-06, "epoch": 1.359508041627247, "percentage": 67.92, "elapsed_time": "1:56:30", "remaining_time": "0:55:00"}
+{"current_steps": 370, "total_steps": 530, "loss": 0.129, "lr": 2.5572529500402365e-06, "epoch": 1.3973509933774835, "percentage": 69.81, "elapsed_time": "1:59:42", "remaining_time": "0:51:46"}
+{"current_steps": 380, "total_steps": 530, "loss": 0.1205, "lr": 2.275424070459803e-06, "epoch": 1.43519394512772, "percentage": 71.7, "elapsed_time": "2:02:56", "remaining_time": "0:48:31"}
+{"current_steps": 390, "total_steps": 530, "loss": 0.129, "lr": 2.005409406946e-06, "epoch": 1.4730368968779564, "percentage": 73.58, "elapsed_time": "2:06:14", "remaining_time": "0:45:18"}
+{"current_steps": 400, "total_steps": 530, "loss": 0.1209, "lr": 1.7483797881556175e-06, "epoch": 1.5108798486281931, "percentage": 75.47, "elapsed_time": "2:09:25", "remaining_time": "0:42:03"}
+{"current_steps": 400, "total_steps": 530, "eval_loss": 0.1692177653312683, "epoch": 1.5108798486281931, "percentage": 75.47, "elapsed_time": "2:10:59", "remaining_time": "0:42:34"}
+{"current_steps": 410, "total_steps": 530, "loss": 0.1155, "lr": 1.5054497374238275e-06, "epoch": 1.5487228003784295, "percentage": 77.36, "elapsed_time": "2:14:12", "remaining_time": "0:39:16"}
+{"current_steps": 420, "total_steps": 530, "loss": 0.1193, "lr": 1.277672640004936e-06, "epoch": 1.586565752128666, "percentage": 79.25, "elapsed_time": "2:17:22", "remaining_time": "0:35:58"}
+{"current_steps": 430, "total_steps": 530, "loss": 0.115, "lr": 1.066036175418082e-06, "epoch": 1.6244087038789026, "percentage": 81.13, "elapsed_time": "2:20:35", "remaining_time": "0:32:41"}
+{"current_steps": 440, "total_steps": 530, "loss": 0.1162, "lr": 8.714580347039491e-07, "epoch": 1.6622516556291391, "percentage": 83.02, "elapsed_time": "2:23:43", "remaining_time": "0:29:23"}
+{"current_steps": 450, "total_steps": 530, "loss": 0.1138, "lr": 6.947819411632223e-07, "epoch": 1.7000946073793757, "percentage": 84.91, "elapsed_time": "2:26:53", "remaining_time": "0:26:06"}
+{"current_steps": 460, "total_steps": 530, "loss": 0.112, "lr": 5.367739918315068e-07, "epoch": 1.737937559129612, "percentage": 86.79, "elapsed_time": "2:30:09", "remaining_time": "0:22:50"}
+{"current_steps": 470, "total_steps": 530, "loss": 0.1098, "lr": 3.98119335554687e-07, "epoch": 1.7757805108798488, "percentage": 88.68, "elapsed_time": "2:33:23", "remaining_time": "0:19:34"}
+{"current_steps": 480, "total_steps": 530, "loss": 0.1152, "lr": 2.7941920206915443e-07, "epoch": 1.8136234626300851, "percentage": 90.57, "elapsed_time": "2:36:33", "remaining_time": "0:16:18"}
+{"current_steps": 490, "total_steps": 530, "loss": 0.1051, "lr": 1.8118829496930557e-07, "epoch": 1.8514664143803217, "percentage": 92.45, "elapsed_time": "2:39:44", "remaining_time": "0:13:02"}
+{"current_steps": 500, "total_steps": 530, "loss": 0.1053, "lr": 1.0385255986682718e-07, "epoch": 1.8893093661305582, "percentage": 94.34, "elapsed_time": "2:42:56", "remaining_time": "0:09:46"}
+{"current_steps": 510, "total_steps": 530, "loss": 0.1044, "lr": 4.774733741942206e-08, "epoch": 1.9271523178807946, "percentage": 96.23, "elapsed_time": "2:46:08", "remaining_time": "0:06:30"}
+{"current_steps": 520, "total_steps": 530, "loss": 0.1083, "lr": 1.3115909237734203e-08, "epoch": 1.9649952696310313, "percentage": 98.11, "elapsed_time": "2:49:21", "remaining_time": "0:03:15"}
+{"current_steps": 530, "total_steps": 530, "loss": 0.1132, "lr": 1.0844297567258466e-10, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "2:52:22", "remaining_time": "0:00:00"}
+{"current_steps": 530, "total_steps": 530, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "2:52:43", "remaining_time": "0:00:00"}

test_admin/trainer_state.json

@@ -0,0 +1,430 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 200,
+  "global_step": 530,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03784295175023652,
+      "grad_norm": 12.928278923034668,
+      "learning_rate": 1.6981132075471698e-06,
+      "loss": 1.4503,
+      "step": 10
+    },
+    {
+      "epoch": 0.07568590350047304,
+      "grad_norm": 4.828810214996338,
+      "learning_rate": 3.5849056603773586e-06,
+      "loss": 0.8761,
+      "step": 20
+    },
+    {
+      "epoch": 0.11352885525070956,
+      "grad_norm": 3.0466108322143555,
+      "learning_rate": 5.4716981132075475e-06,
+      "loss": 0.5782,
+      "step": 30
+    },
+    {
+      "epoch": 0.15137180700094607,
+      "grad_norm": 2.7793734073638916,
+      "learning_rate": 7.358490566037736e-06,
+      "loss": 0.4365,
+      "step": 40
+    },
+    {
+      "epoch": 0.1892147587511826,
+      "grad_norm": 2.6989638805389404,
+      "learning_rate": 9.245283018867926e-06,
+      "loss": 0.3779,
+      "step": 50
+    },
+    {
+      "epoch": 0.22705771050141912,
+      "grad_norm": 2.662125825881958,
+      "learning_rate": 9.99609654676786e-06,
+      "loss": 0.3345,
+      "step": 60
+    },
+    {
+      "epoch": 0.26490066225165565,
+      "grad_norm": 2.1630754470825195,
+      "learning_rate": 9.9722641784023e-06,
+      "loss": 0.3279,
+      "step": 70
+    },
+    {
+      "epoch": 0.30274361400189215,
+      "grad_norm": 2.4073753356933594,
+      "learning_rate": 9.92687124249773e-06,
+      "loss": 0.3057,
+      "step": 80
+    },
+    {
+      "epoch": 0.34058656575212864,
+      "grad_norm": 2.1243770122528076,
+      "learning_rate": 9.860114570402055e-06,
+      "loss": 0.2971,
+      "step": 90
+    },
+    {
+      "epoch": 0.3784295175023652,
+      "grad_norm": 2.0397891998291016,
+      "learning_rate": 9.772283630189727e-06,
+      "loss": 0.2811,
+      "step": 100
+    },
+    {
+      "epoch": 0.4162724692526017,
+      "grad_norm": 2.167642116546631,
+      "learning_rate": 9.663759271479858e-06,
+      "loss": 0.2664,
+      "step": 110
+    },
+    {
+      "epoch": 0.45411542100283825,
+      "grad_norm": 2.2073721885681152,
+      "learning_rate": 9.535012074008688e-06,
+      "loss": 0.2721,
+      "step": 120
+    },
+    {
+      "epoch": 0.49195837275307475,
+      "grad_norm": 2.113102912902832,
+      "learning_rate": 9.386600307117293e-06,
+      "loss": 0.2549,
+      "step": 130
+    },
+    {
+      "epoch": 0.5298013245033113,
+      "grad_norm": 1.9171561002731323,
+      "learning_rate": 9.219167509002526e-06,
+      "loss": 0.2534,
+      "step": 140
+    },
+    {
+      "epoch": 0.5676442762535477,
+      "grad_norm": 1.8712971210479736,
+      "learning_rate": 9.033439696227966e-06,
+      "loss": 0.2447,
+      "step": 150
+    },
+    {
+      "epoch": 0.6054872280037843,
+      "grad_norm": 2.0216710567474365,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.2491,
+      "step": 160
+    },
+    {
+      "epoch": 0.6433301797540208,
+      "grad_norm": 1.623536229133606,
+      "learning_rate": 8.610396252024113e-06,
+      "loss": 0.2397,
+      "step": 170
+    },
+    {
+      "epoch": 0.6811731315042573,
+      "grad_norm": 1.9642530679702759,
+      "learning_rate": 8.374915007591053e-06,
+      "loss": 0.2172,
+      "step": 180
+    },
+    {
+      "epoch": 0.7190160832544938,
+      "grad_norm": 1.723118543624878,
+      "learning_rate": 8.124799568282418e-06,
+      "loss": 0.234,
+      "step": 190
+    },
+    {
+      "epoch": 0.7568590350047304,
+      "grad_norm": 1.7284762859344482,
+      "learning_rate": 7.861134476396903e-06,
+      "loss": 0.2217,
+      "step": 200
+    },
+    {
+      "epoch": 0.7568590350047304,
+      "eval_loss": 0.2220437228679657,
+      "eval_runtime": 93.3051,
+      "eval_samples_per_second": 8.821,
+      "eval_steps_per_second": 1.265,
+      "step": 200
+    },
+    {
+      "epoch": 0.7947019867549668,
+      "grad_norm": 1.6118355989456177,
+      "learning_rate": 7.58506302778873e-06,
+      "loss": 0.2129,
+      "step": 210
+    },
+    {
+      "epoch": 0.8325449385052034,
+      "grad_norm": 1.7828593254089355,
+      "learning_rate": 7.297782314345972e-06,
+      "loss": 0.2146,
+      "step": 220
+    },
+    {
+      "epoch": 0.8703878902554399,
+      "grad_norm": 1.4980388879776,
+      "learning_rate": 7.00053803320028e-06,
+      "loss": 0.1948,
+      "step": 230
+    },
+    {
+      "epoch": 0.9082308420056765,
+      "grad_norm": 1.5348376035690308,
+      "learning_rate": 6.694619085176159e-06,
+      "loss": 0.2056,
+      "step": 240
+    },
+    {
+      "epoch": 0.9460737937559129,
+      "grad_norm": 1.3809292316436768,
+      "learning_rate": 6.381351985901842e-06,
+      "loss": 0.1986,
+      "step": 250
+    },
+    {
+      "epoch": 0.9839167455061495,
+      "grad_norm": 1.3319153785705566,
+      "learning_rate": 6.062095113816069e-06,
+      "loss": 0.1962,
+      "step": 260
+    },
+    {
+      "epoch": 1.0189214758751182,
+      "grad_norm": 1.361677885055542,
+      "learning_rate": 5.738232820012407e-06,
+      "loss": 0.1666,
+      "step": 270
+    },
+    {
+      "epoch": 1.0567644276253547,
+      "grad_norm": 1.4107803106307983,
+      "learning_rate": 5.411169425461822e-06,
+      "loss": 0.1459,
+      "step": 280
+    },
+    {
+      "epoch": 1.0946073793755913,
+      "grad_norm": 1.373854637145996,
+      "learning_rate": 5.082323131642496e-06,
+      "loss": 0.1453,
+      "step": 290
+    },
+    {
+      "epoch": 1.1324503311258278,
+      "grad_norm": 1.3363025188446045,
+      "learning_rate": 4.753119870981486e-06,
+      "loss": 0.1401,
+      "step": 300
+    },
+    {
+      "epoch": 1.1702932828760644,
+      "grad_norm": 1.3609431982040405,
+      "learning_rate": 4.424987123773654e-06,
+      "loss": 0.132,
+      "step": 310
+    },
+    {
+      "epoch": 1.208136234626301,
+      "grad_norm": 1.300492286682129,
+      "learning_rate": 4.0993477283888264e-06,
+      "loss": 0.1342,
+      "step": 320
+    },
+    {
+      "epoch": 1.2459791863765375,
+      "grad_norm": 1.1971514225006104,
+      "learning_rate": 3.777613711607087e-06,
+      "loss": 0.1322,
+      "step": 330
+    },
+    {
+      "epoch": 1.2838221381267738,
+      "grad_norm": 1.4877253770828247,
+      "learning_rate": 3.46118016583494e-06,
+      "loss": 0.1368,
+      "step": 340
+    },
+    {
+      "epoch": 1.3216650898770104,
+      "grad_norm": 1.2842473983764648,
+      "learning_rate": 3.1514191997517387e-06,
+      "loss": 0.1301,
+      "step": 350
+    },
+    {
+      "epoch": 1.359508041627247,
+      "grad_norm": 1.3692116737365723,
+      "learning_rate": 2.8496739886173994e-06,
+      "loss": 0.1314,
+      "step": 360
+    },
+    {
+      "epoch": 1.3973509933774835,
+      "grad_norm": 1.254835605621338,
+      "learning_rate": 2.5572529500402365e-06,
+      "loss": 0.129,
+      "step": 370
+    },
+    {
+      "epoch": 1.43519394512772,
+      "grad_norm": 1.2396975755691528,
+      "learning_rate": 2.275424070459803e-06,
+      "loss": 0.1205,
+      "step": 380
+    },
+    {
+      "epoch": 1.4730368968779564,
+      "grad_norm": 1.3641499280929565,
+      "learning_rate": 2.005409406946e-06,
+      "loss": 0.129,
+      "step": 390
+    },
+    {
+      "epoch": 1.5108798486281931,
+      "grad_norm": 1.4750701189041138,
+      "learning_rate": 1.7483797881556175e-06,
+      "loss": 0.1209,
+      "step": 400
+    },
+    {
+      "epoch": 1.5108798486281931,
+      "eval_loss": 0.1692177653312683,
+      "eval_runtime": 94.0494,
+      "eval_samples_per_second": 8.751,
+      "eval_steps_per_second": 1.255,
+      "step": 400
+    },
+    {
+      "epoch": 1.5487228003784295,
+      "grad_norm": 1.1940029859542847,
+      "learning_rate": 1.5054497374238275e-06,
+      "loss": 0.1155,
+      "step": 410
+    },
+    {
+      "epoch": 1.586565752128666,
+      "grad_norm": 1.2632642984390259,
+      "learning_rate": 1.277672640004936e-06,
+      "loss": 0.1193,
+      "step": 420
+    },
+    {
+      "epoch": 1.6244087038789026,
+      "grad_norm": 1.2763444185256958,
+      "learning_rate": 1.066036175418082e-06,
+      "loss": 0.115,
+      "step": 430
+    },
+    {
+      "epoch": 1.6622516556291391,
+      "grad_norm": 1.2933067083358765,
+      "learning_rate": 8.714580347039491e-07,
+      "loss": 0.1162,
+      "step": 440
+    },
+    {
+      "epoch": 1.7000946073793757,
+      "grad_norm": 1.197369933128357,
+      "learning_rate": 6.947819411632223e-07,
+      "loss": 0.1138,
+      "step": 450
+    },
+    {
+      "epoch": 1.737937559129612,
+      "grad_norm": 1.1830955743789673,
+      "learning_rate": 5.367739918315068e-07,
+      "loss": 0.112,
+      "step": 460
+    },
+    {
+      "epoch": 1.7757805108798488,
+      "grad_norm": 1.2318562269210815,
+      "learning_rate": 3.98119335554687e-07,
+      "loss": 0.1098,
+      "step": 470
+    },
+    {
+      "epoch": 1.8136234626300851,
+      "grad_norm": 1.2451008558273315,
+      "learning_rate": 2.7941920206915443e-07,
+      "loss": 0.1152,
+      "step": 480
+    },
+    {
+      "epoch": 1.8514664143803217,
+      "grad_norm": 1.2878820896148682,
+      "learning_rate": 1.8118829496930557e-07,
+      "loss": 0.1051,
+      "step": 490
+    },
+    {
+      "epoch": 1.8893093661305582,
+      "grad_norm": 1.2973670959472656,
+      "learning_rate": 1.0385255986682718e-07,
+      "loss": 0.1053,
+      "step": 500
+    },
+    {
+      "epoch": 1.9271523178807946,
+      "grad_norm": 1.1544054746627808,
+      "learning_rate": 4.774733741942206e-08,
+      "loss": 0.1044,
+      "step": 510
+    },
+    {
+      "epoch": 1.9649952696310313,
+      "grad_norm": 1.1692767143249512,
+      "learning_rate": 1.3115909237734203e-08,
+      "loss": 0.1083,
+      "step": 520
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.188850164413452,
+      "learning_rate": 1.0844297567258466e-10,
+      "loss": 0.1132,
+      "step": 530
+    },
+    {
+      "epoch": 2.0,
+      "step": 530,
+      "total_flos": 71607640850432.0,
+      "train_loss": 0.2318565127984533,
+      "train_runtime": 10363.9156,
+      "train_samples_per_second": 1.428,
+      "train_steps_per_second": 0.051
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 530,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 71607640850432.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

test_admin/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a37020c5a151476675a0de908b396c66c9fd45acf7ce6ec0e6003f9a71e5165
+size 8273