初始化项目，由ModelHub XC社区提供模型

Model: MBZUAI/DAFT
Source: Original Platform

.gitattributes

@@ -0,0 +1,52 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+vocab.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text
+merges.txt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Qwen/Qwen3-0.6B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: daft-qwen3
+  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. -->
+
+# daft-qwen3
+
+This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) on the daft_sharegpt 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- 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_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.55.0
+- Pytorch 2.8.0+rocm6.3
+- Datasets 3.6.0
+- Tokenizers 0.21.1

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.3702381181159342e+18,
+    "train_loss": 0.11128336125916809,
+    "train_runtime": 25797.0773,
+    "train_samples_per_second": 1.359,
+    "train_steps_per_second": 0.011
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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 message.content is string 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.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.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' }}
+        {{- 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 %}

config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.55.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f162b77cc2cb0abd9bf2f73a59c3fe3007e0425aeae88f9f4cad0410ce69640
+size 1503300328

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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.3702381181159342e+18,
+    "train_loss": 0.11128336125916809,
+    "train_runtime": 25797.0773,
+    "train_samples_per_second": 1.359,
+    "train_steps_per_second": 0.011
+}

trainer_log.jsonl

@@ -0,0 +1,31 @@
+{"current_steps": 10, "total_steps": 592, "loss": 0.9248, "lr": 3e-06, "epoch": 0.016918684572274505, "percentage": 1.69, "elapsed_time": "0:18:41", "remaining_time": "18:07:54"}
+{"current_steps": 20, "total_steps": 592, "loss": 0.7809, "lr": 6.333333333333333e-06, "epoch": 0.03383736914454901, "percentage": 3.38, "elapsed_time": "0:39:12", "remaining_time": "18:41:34"}
+{"current_steps": 30, "total_steps": 592, "loss": 0.5233, "lr": 9.666666666666667e-06, "epoch": 0.05075605371682352, "percentage": 5.07, "elapsed_time": "0:58:13", "remaining_time": "18:10:46"}
+{"current_steps": 10, "total_steps": 274, "loss": 0.7733, "lr": 6.4285714285714295e-06, "epoch": 0.0364963503649635, "percentage": 3.65, "elapsed_time": "0:16:11", "remaining_time": "7:07:31"}
+{"current_steps": 20, "total_steps": 274, "loss": 0.55, "lr": 1.3571428571428574e-05, "epoch": 0.072992700729927, "percentage": 7.3, "elapsed_time": "0:32:40", "remaining_time": "6:55:01"}
+{"current_steps": 30, "total_steps": 274, "loss": 0.2368, "lr": 1.9999184556954777e-05, "epoch": 0.10948905109489052, "percentage": 10.95, "elapsed_time": "0:48:55", "remaining_time": "6:37:54"}
+{"current_steps": 40, "total_steps": 274, "loss": 0.1277, "lr": 1.9901492206471325e-05, "epoch": 0.145985401459854, "percentage": 14.6, "elapsed_time": "1:04:35", "remaining_time": "6:17:51"}
+{"current_steps": 50, "total_steps": 274, "loss": 0.1016, "lr": 1.964253495453141e-05, "epoch": 0.18248175182481752, "percentage": 18.25, "elapsed_time": "1:19:24", "remaining_time": "5:55:44"}
+{"current_steps": 60, "total_steps": 274, "loss": 0.0831, "lr": 1.9226530419534834e-05, "epoch": 0.21897810218978103, "percentage": 21.9, "elapsed_time": "1:35:23", "remaining_time": "5:40:13"}
+{"current_steps": 70, "total_steps": 274, "loss": 0.0815, "lr": 1.866025403784439e-05, "epoch": 0.25547445255474455, "percentage": 25.55, "elapsed_time": "1:52:09", "remaining_time": "5:26:50"}
+{"current_steps": 80, "total_steps": 274, "loss": 0.0722, "lr": 1.7952928712734266e-05, "epoch": 0.291970802919708, "percentage": 29.2, "elapsed_time": "2:08:51", "remaining_time": "5:12:27"}
+{"current_steps": 90, "total_steps": 274, "loss": 0.0686, "lr": 1.7116074601618418e-05, "epoch": 0.3284671532846715, "percentage": 32.85, "elapsed_time": "2:23:57", "remaining_time": "4:54:19"}
+{"current_steps": 100, "total_steps": 274, "loss": 0.0648, "lr": 1.6163321488063636e-05, "epoch": 0.36496350364963503, "percentage": 36.5, "elapsed_time": "2:39:34", "remaining_time": "4:37:39"}
+{"current_steps": 110, "total_steps": 274, "loss": 0.062, "lr": 1.5110186794471105e-05, "epoch": 0.40145985401459855, "percentage": 40.15, "elapsed_time": "2:55:36", "remaining_time": "4:21:48"}
+{"current_steps": 120, "total_steps": 274, "loss": 0.0571, "lr": 1.3973822850918055e-05, "epoch": 0.43795620437956206, "percentage": 43.8, "elapsed_time": "3:10:37", "remaining_time": "4:04:38"}
+{"current_steps": 130, "total_steps": 274, "loss": 0.0573, "lr": 1.277273753637408e-05, "epoch": 0.4744525547445255, "percentage": 47.45, "elapsed_time": "3:25:35", "remaining_time": "3:47:44"}
+{"current_steps": 140, "total_steps": 274, "loss": 0.053, "lr": 1.1526492842188746e-05, "epoch": 0.5109489051094891, "percentage": 51.09, "elapsed_time": "3:40:38", "remaining_time": "3:31:10"}
+{"current_steps": 150, "total_steps": 274, "loss": 0.0508, "lr": 1.0255386267325602e-05, "epoch": 0.5474452554744526, "percentage": 54.74, "elapsed_time": "3:57:13", "remaining_time": "3:16:06"}
+{"current_steps": 160, "total_steps": 274, "loss": 0.0532, "lr": 8.98012023443585e-06, "epoch": 0.583941605839416, "percentage": 58.39, "elapsed_time": "4:12:36", "remaining_time": "2:59:58"}
+{"current_steps": 170, "total_steps": 274, "loss": 0.0521, "lr": 7.721464910968628e-06, "epoch": 0.6204379562043796, "percentage": 62.04, "elapsed_time": "4:28:29", "remaining_time": "2:44:15"}
+{"current_steps": 180, "total_steps": 274, "loss": 0.0466, "lr": 6.499919926926566e-06, "epoch": 0.656934306569343, "percentage": 65.69, "elapsed_time": "4:43:20", "remaining_time": "2:27:57"}
+{"current_steps": 190, "total_steps": 274, "loss": 0.0517, "lr": 5.335380498845559e-06, "epoch": 0.6934306569343066, "percentage": 69.34, "elapsed_time": "4:59:08", "remaining_time": "2:12:15"}
+{"current_steps": 200, "total_steps": 274, "loss": 0.0565, "lr": 4.2468133978137945e-06, "epoch": 0.7299270072992701, "percentage": 72.99, "elapsed_time": "5:14:51", "remaining_time": "1:56:29"}
+{"current_steps": 210, "total_steps": 274, "loss": 0.0485, "lr": 3.2519480390159806e-06, "epoch": 0.7664233576642335, "percentage": 76.64, "elapsed_time": "5:29:53", "remaining_time": "1:40:32"}
+{"current_steps": 220, "total_steps": 274, "loss": 0.0491, "lr": 2.366987724005404e-06, "epoch": 0.8029197080291971, "percentage": 80.29, "elapsed_time": "5:45:37", "remaining_time": "1:24:50"}
+{"current_steps": 230, "total_steps": 274, "loss": 0.0431, "lr": 1.6063457386805004e-06, "epoch": 0.8394160583941606, "percentage": 83.94, "elapsed_time": "6:01:48", "remaining_time": "1:09:12"}
+{"current_steps": 240, "total_steps": 274, "loss": 0.0542, "lr": 9.82410605119486e-07, "epoch": 0.8759124087591241, "percentage": 87.59, "elapsed_time": "6:17:45", "remaining_time": "0:53:30"}
+{"current_steps": 250, "total_steps": 274, "loss": 0.0473, "lr": 5.053443105997069e-07, "epoch": 0.9124087591240876, "percentage": 91.24, "elapsed_time": "6:32:52", "remaining_time": "0:37:42"}
+{"current_steps": 260, "total_steps": 274, "loss": 0.0446, "lr": 1.8291680003145074e-07, "epoch": 0.948905109489051, "percentage": 94.89, "elapsed_time": "6:48:12", "remaining_time": "0:21:58"}
+{"current_steps": 270, "total_steps": 274, "loss": 0.0467, "lr": 2.037942741615617e-08, "epoch": 0.9854014598540146, "percentage": 98.54, "elapsed_time": "7:03:28", "remaining_time": "0:06:16"}
+{"current_steps": 274, "total_steps": 274, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "7:09:53", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,232 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 274,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0364963503649635,
+      "grad_norm": 2.037085771560669,
+      "learning_rate": 6.4285714285714295e-06,
+      "loss": 0.7733,
+      "step": 10
+    },
+    {
+      "epoch": 0.072992700729927,
+      "grad_norm": 1.040379524230957,
+      "learning_rate": 1.3571428571428574e-05,
+      "loss": 0.55,
+      "step": 20
+    },
+    {
+      "epoch": 0.10948905109489052,
+      "grad_norm": 1.7783838510513306,
+      "learning_rate": 1.9999184556954777e-05,
+      "loss": 0.2368,
+      "step": 30
+    },
+    {
+      "epoch": 0.145985401459854,
+      "grad_norm": 0.8324124217033386,
+      "learning_rate": 1.9901492206471325e-05,
+      "loss": 0.1277,
+      "step": 40
+    },
+    {
+      "epoch": 0.18248175182481752,
+      "grad_norm": 0.272566020488739,
+      "learning_rate": 1.964253495453141e-05,
+      "loss": 0.1016,
+      "step": 50
+    },
+    {
+      "epoch": 0.21897810218978103,
+      "grad_norm": 0.3388763666152954,
+      "learning_rate": 1.9226530419534834e-05,
+      "loss": 0.0831,
+      "step": 60
+    },
+    {
+      "epoch": 0.25547445255474455,
+      "grad_norm": 0.16205106675624847,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.0815,
+      "step": 70
+    },
+    {
+      "epoch": 0.291970802919708,
+      "grad_norm": 0.17601074278354645,
+      "learning_rate": 1.7952928712734266e-05,
+      "loss": 0.0722,
+      "step": 80
+    },
+    {
+      "epoch": 0.3284671532846715,
+      "grad_norm": 0.33516547083854675,
+      "learning_rate": 1.7116074601618418e-05,
+      "loss": 0.0686,
+      "step": 90
+    },
+    {
+      "epoch": 0.36496350364963503,
+      "grad_norm": 0.2756238877773285,
+      "learning_rate": 1.6163321488063636e-05,
+      "loss": 0.0648,
+      "step": 100
+    },
+    {
+      "epoch": 0.40145985401459855,
+      "grad_norm": 0.357218474149704,
+      "learning_rate": 1.5110186794471105e-05,
+      "loss": 0.062,
+      "step": 110
+    },
+    {
+      "epoch": 0.43795620437956206,
+      "grad_norm": 0.20831607282161713,
+      "learning_rate": 1.3973822850918055e-05,
+      "loss": 0.0571,
+      "step": 120
+    },
+    {
+      "epoch": 0.4744525547445255,
+      "grad_norm": 0.2679807245731354,
+      "learning_rate": 1.277273753637408e-05,
+      "loss": 0.0573,
+      "step": 130
+    },
+    {
+      "epoch": 0.5109489051094891,
+      "grad_norm": 0.2546704411506653,
+      "learning_rate": 1.1526492842188746e-05,
+      "loss": 0.053,
+      "step": 140
+    },
+    {
+      "epoch": 0.5474452554744526,
+      "grad_norm": 0.1792953908443451,
+      "learning_rate": 1.0255386267325602e-05,
+      "loss": 0.0508,
+      "step": 150
+    },
+    {
+      "epoch": 0.583941605839416,
+      "grad_norm": 0.17367389798164368,
+      "learning_rate": 8.98012023443585e-06,
+      "loss": 0.0532,
+      "step": 160
+    },
+    {
+      "epoch": 0.6204379562043796,
+      "grad_norm": 0.14929895102977753,
+      "learning_rate": 7.721464910968628e-06,
+      "loss": 0.0521,
+      "step": 170
+    },
+    {
+      "epoch": 0.656934306569343,
+      "grad_norm": 0.17261824011802673,
+      "learning_rate": 6.499919926926566e-06,
+      "loss": 0.0466,
+      "step": 180
+    },
+    {
+      "epoch": 0.6934306569343066,
+      "grad_norm": 0.1643795520067215,
+      "learning_rate": 5.335380498845559e-06,
+      "loss": 0.0517,
+      "step": 190
+    },
+    {
+      "epoch": 0.7299270072992701,
+      "grad_norm": 0.14236749708652496,
+      "learning_rate": 4.2468133978137945e-06,
+      "loss": 0.0565,
+      "step": 200
+    },
+    {
+      "epoch": 0.7664233576642335,
+      "grad_norm": 0.15162824094295502,
+      "learning_rate": 3.2519480390159806e-06,
+      "loss": 0.0485,
+      "step": 210
+    },
+    {
+      "epoch": 0.8029197080291971,
+      "grad_norm": 0.13050702214241028,
+      "learning_rate": 2.366987724005404e-06,
+      "loss": 0.0491,
+      "step": 220
+    },
+    {
+      "epoch": 0.8394160583941606,
+      "grad_norm": 0.11725970357656479,
+      "learning_rate": 1.6063457386805004e-06,
+      "loss": 0.0431,
+      "step": 230
+    },
+    {
+      "epoch": 0.8759124087591241,
+      "grad_norm": 0.1599208265542984,
+      "learning_rate": 9.82410605119486e-07,
+      "loss": 0.0542,
+      "step": 240
+    },
+    {
+      "epoch": 0.9124087591240876,
+      "grad_norm": 0.1203792542219162,
+      "learning_rate": 5.053443105997069e-07,
+      "loss": 0.0473,
+      "step": 250
+    },
+    {
+      "epoch": 0.948905109489051,
+      "grad_norm": 0.11177993565797806,
+      "learning_rate": 1.8291680003145074e-07,
+      "loss": 0.0446,
+      "step": 260
+    },
+    {
+      "epoch": 0.9854014598540146,
+      "grad_norm": 0.0998225063085556,
+      "learning_rate": 2.037942741615617e-08,
+      "loss": 0.0467,
+      "step": 270
+    },
+    {
+      "epoch": 1.0,
+      "step": 274,
+      "total_flos": 1.3702381181159342e+18,
+      "train_loss": 0.11128336125916809,
+      "train_runtime": 25797.0773,
+      "train_samples_per_second": 1.359,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 274,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3702381181159342e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}