初始化项目，由ModelHub XC社区提供模型

Model: lldois/v52_public091_full_lr2e5_ep1
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+library_name: transformers
+license: other
+base_model: OpenOneRec/OneReason-0.8B-pretrain-competition
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: v52_public091_full_lr2e5_ep1
+  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. -->
+
+# v52_public091_full_lr2e5_ep1
+
+This model is a fine-tuned version of [OpenOneRec/OneReason-0.8B-pretrain-competition](https://huggingface.co/OpenOneRec/OneReason-0.8B-pretrain-competition) on the exp_v49_public_091_exact 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: 202607202
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.03
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.6.0
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.563295846805975e+17,
+    "train_loss": 1.6355595296145948,
+    "train_runtime": 2594.717,
+    "train_samples_per_second": 0.503,
+    "train_steps_per_second": 0.126
+}

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 +1,63 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 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,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.6.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 176253
+}

experiment_recipe.json

@@ -0,0 +1,77 @@
+{
+  "created_at": "2026-07-16 23:52:50",
+  "name": "v52_public091_full_lr2e5_ep1",
+  "base": "OpenOneRec/OneReason-0.8B-pretrain-competition",
+  "dataset": "v49_public_091_exact",
+  "dataset_manifest": {
+    "path": "/home/ll/llm4rec/experiments/data/v49_public_091_exact.jsonl",
+    "records": 32705,
+    "groups": {
+      "rec": 18651,
+      "item": 9684,
+      "user": 2792,
+      "world": 1578
+    },
+    "routes": {
+      "no_think": 20934,
+      "think": 11771
+    },
+    "thought_modes": {
+      "empty": 20934,
+      "filled": 11771
+    },
+    "sha256": "cdedea13c560d3453697f4a3c9b96a2303bd708c84833034fa953d16482b9925",
+    "source_path": "/home/ll/llm4rec/data/external/kuaishou-llmrec-sft-baseline-0.91/train.jsonl",
+    "source_url": "https://huggingface.co/datasets/Frinkleko/kuaishou-llmrec-sft-baseline-0.91/resolve/main/train.jsonl?download=true",
+    "source_sha256": "4d6b29d76974c9a1517c1b583858e744cae019cb26e1e2d90066e237ebbcf5f8",
+    "source_license": "Apache-2.0",
+    "transform": "Lossless field mapping from system/prompt/response to instruction/input/output; original seed-42 order retained."
+  },
+  "learning_rate": "2.0e-5",
+  "epochs": 1.0,
+  "method": "full",
+  "weight_decay": 0.0,
+  "validation_size": 0.0,
+  "lora": {
+    "rank": null,
+    "alpha": null,
+    "dropout": null,
+    "target": null
+  },
+  "stages": null,
+  "note": "Full-SFT counterpart using v7's successful 2e-5 scale, now on balanced CoT/direct clean data instead of final-only data.",
+  "evaluation": null,
+  "cot_policy": "Preserve meaningful CoT for /think and pure final outputs for /no_think.",
+  "checkpoint_policy": "save_strategy=no; only the final model is retained.",
+  "script": "/home/ll/llm4rec/experiments/run_experiments.py",
+  "script_sha256": "bc57a4d1337c7182996ece63ddc844185043b68ae2a2dbe793e3969bbccc2e2d",
+  "data_builder": "/home/ll/llm4rec/experiments/source_data.py",
+  "data_builder_sha256": "a1216b14c8c516f9fde2fcaab9d70ec5b8a200033fbd1ee330c6b461213587ad",
+  "data_cleaner": null,
+  "data_cleaner_sha256": null,
+  "configs": [
+    "/home/ll/llm4rec/experiments/configs/v52_public091_full_lr2e5_ep1.yaml"
+  ],
+  "reproduce": "/home/ll/llm4rec/demo/LLaMA-Factory/.venv/bin/python /home/ll/llm4rec/experiments/run_experiments.py --single v52_public091_full_lr2e5_ep1 --gpu <gpu>",
+  "training_result": {
+    "name": "v52_public091_full_lr2e5_ep1",
+    "gpu": 1,
+    "started_at": "2026-07-17 01:41:03",
+    "status": "ok",
+    "wall_seconds": 2611.22,
+    "finished_at": "2026-07-17 02:24:34",
+    "epoch": 1.0,
+    "total_flos": 1.563295846805975e+17,
+    "train_loss": 1.6355595296145948,
+    "train_runtime": 2594.717,
+    "train_samples_per_second": 0.503,
+    "train_steps_per_second": 0.126,
+    "global_step": 326,
+    "first_logged_loss": 2.659077453613281,
+    "last_logged_loss": 1.512490463256836,
+    "min_logged_loss": 1.5008227348327636,
+    "tail_loss_mean": 1.5448276201883953,
+    "logged_loss_change": -1.1465869903564452,
+    "batch": "v49-v53"
+  }
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.6.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8f026ea380644a0869b10aee9df9288534d15a1ca9e1b2f9b25383de60db9ed
+size 1602902832

runs/Jul17_01-41-18_ubuntu-System-Product-Name/events.out.tfevents.1784223678.ubuntu-System-Product-Name.1430897.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f55f931403f23c73e55a1a6df47f51344a55af18b8882d66fa768d6967f35822
+size 12998

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4d15f596979aecbc11ba12668cb21c9fb8452ce1235cd9d7878cc950170421
+size 16016554

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "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": 1.563295846805975e+17,
+    "train_loss": 1.6355595296145948,
+    "train_runtime": 2594.717,
+    "train_samples_per_second": 0.503,
+    "train_steps_per_second": 0.126
+}

trainer_log.jsonl

@@ -0,0 +1,33 @@
+{"current_steps": 10, "total_steps": 326, "loss": 2.659077453613281, "lr": 1.8e-05, "epoch": 0.03067484662576687, "percentage": 3.07, "elapsed_time": "0:01:19", "remaining_time": "0:41:47"}
+{"current_steps": 20, "total_steps": 326, "loss": 2.113694763183594, "lr": 1.995999715857997e-05, "epoch": 0.06134969325153374, "percentage": 6.13, "elapsed_time": "0:02:36", "remaining_time": "0:39:50"}
+{"current_steps": 30, "total_steps": 326, "loss": 1.8163612365722657, "lr": 1.9822126571413616e-05, "epoch": 0.09202453987730061, "percentage": 9.2, "elapsed_time": "0:03:55", "remaining_time": "0:38:43"}
+{"current_steps": 40, "total_steps": 326, "loss": 1.7940385818481446, "lr": 1.9587255619128648e-05, "epoch": 0.12269938650306748, "percentage": 12.27, "elapsed_time": "0:05:15", "remaining_time": "0:37:34"}
+{"current_steps": 50, "total_steps": 326, "loss": 1.702846145629883, "lr": 1.9257703816543144e-05, "epoch": 0.15337423312883436, "percentage": 15.34, "elapsed_time": "0:06:33", "remaining_time": "0:36:13"}
+{"current_steps": 60, "total_steps": 326, "loss": 1.6503068923950195, "lr": 1.8836725718049562e-05, "epoch": 0.18404907975460122, "percentage": 18.4, "elapsed_time": "0:07:55", "remaining_time": "0:35:08"}
+{"current_steps": 70, "total_steps": 326, "loss": 1.6176418304443358, "lr": 1.8328478776615336e-05, "epoch": 0.2147239263803681, "percentage": 21.47, "elapsed_time": "0:09:14", "remaining_time": "0:33:48"}
+{"current_steps": 80, "total_steps": 326, "loss": 1.649836540222168, "lr": 1.7737982286028938e-05, "epoch": 0.24539877300613497, "percentage": 24.54, "elapsed_time": "0:10:34", "remaining_time": "0:32:31"}
+{"current_steps": 90, "total_steps": 326, "loss": 1.6427200317382813, "lr": 1.7071067811865477e-05, "epoch": 0.27607361963190186, "percentage": 27.61, "elapsed_time": "0:11:54", "remaining_time": "0:31:12"}
+{"current_steps": 100, "total_steps": 326, "loss": 1.5673911094665527, "lr": 1.6334321600700612e-05, "epoch": 0.3067484662576687, "percentage": 30.67, "elapsed_time": "0:13:15", "remaining_time": "0:29:56"}
+{"current_steps": 110, "total_steps": 326, "loss": 1.5665663719177245, "lr": 1.5535019536322158e-05, "epoch": 0.3374233128834356, "percentage": 33.74, "elapsed_time": "0:14:35", "remaining_time": "0:28:38"}
+{"current_steps": 120, "total_steps": 326, "loss": 1.549239158630371, "lr": 1.4681055285292138e-05, "epoch": 0.36809815950920244, "percentage": 36.81, "elapsed_time": "0:15:52", "remaining_time": "0:27:15"}
+{"current_steps": 130, "total_steps": 326, "loss": 1.5795641899108888, "lr": 1.3780862341472183e-05, "epoch": 0.3987730061349693, "percentage": 39.88, "elapsed_time": "0:17:13", "remaining_time": "0:25:58"}
+{"current_steps": 140, "total_steps": 326, "loss": 1.5186445236206054, "lr": 1.2843330739377003e-05, "epoch": 0.4294478527607362, "percentage": 42.94, "elapsed_time": "0:18:34", "remaining_time": "0:24:41"}
+{"current_steps": 150, "total_steps": 326, "loss": 1.5579788208007812, "lr": 1.1877719258869827e-05, "epoch": 0.4601226993865031, "percentage": 46.01, "elapsed_time": "0:19:53", "remaining_time": "0:23:20"}
+{"current_steps": 160, "total_steps": 326, "loss": 1.5645319938659668, "lr": 1.0893563988239773e-05, "epoch": 0.49079754601226994, "percentage": 49.08, "elapsed_time": "0:21:10", "remaining_time": "0:21:57"}
+{"current_steps": 170, "total_steps": 326, "loss": 1.5919049263000489, "lr": 9.900584148664705e-06, "epoch": 0.5214723926380368, "percentage": 52.15, "elapsed_time": "0:22:28", "remaining_time": "0:20:37"}
+{"current_steps": 180, "total_steps": 326, "loss": 1.571799087524414, "lr": 8.908586110108794e-06, "epoch": 0.5521472392638037, "percentage": 55.21, "elapsed_time": "0:23:48", "remaining_time": "0:19:19"}
+{"current_steps": 190, "total_steps": 326, "loss": 1.5389130592346192, "lr": 7.927366546564911e-06, "epoch": 0.5828220858895705, "percentage": 58.28, "elapsed_time": "0:25:07", "remaining_time": "0:17:59"}
+{"current_steps": 200, "total_steps": 326, "loss": 1.5266441345214843, "lr": 6.966615687051517e-06, "epoch": 0.6134969325153374, "percentage": 61.35, "elapsed_time": "0:26:29", "remaining_time": "0:16:41"}
+{"current_steps": 210, "total_steps": 326, "loss": 1.5582975387573241, "lr": 6.03582161782806e-06, "epoch": 0.6441717791411042, "percentage": 64.42, "elapsed_time": "0:27:49", "remaining_time": "0:15:22"}
+{"current_steps": 220, "total_steps": 326, "loss": 1.5671936988830566, "lr": 5.144176580911431e-06, "epoch": 0.6748466257668712, "percentage": 67.48, "elapsed_time": "0:29:07", "remaining_time": "0:14:01"}
+{"current_steps": 230, "total_steps": 326, "loss": 1.5731188774108886, "lr": 4.3004861942610575e-06, "epoch": 0.7055214723926381, "percentage": 70.55, "elapsed_time": "0:30:25", "remaining_time": "0:12:42"}
+{"current_steps": 240, "total_steps": 326, "loss": 1.5142654418945312, "lr": 3.513082490146864e-06, "epoch": 0.7361963190184049, "percentage": 73.62, "elapsed_time": "0:31:46", "remaining_time": "0:11:23"}
+{"current_steps": 250, "total_steps": 326, "loss": 1.5008227348327636, "lr": 2.7897416305068325e-06, "epoch": 0.7668711656441718, "percentage": 76.69, "elapsed_time": "0:33:07", "remaining_time": "0:10:04"}
+{"current_steps": 260, "total_steps": 326, "loss": 1.585028839111328, "lr": 2.137607111912734e-06, "epoch": 0.7975460122699386, "percentage": 79.75, "elapsed_time": "0:34:23", "remaining_time": "0:08:43"}
+{"current_steps": 270, "total_steps": 326, "loss": 1.571006679534912, "lr": 1.5631192185484557e-06, "epoch": 0.8282208588957055, "percentage": 82.82, "elapsed_time": "0:35:44", "remaining_time": "0:07:24"}
+{"current_steps": 280, "total_steps": 326, "loss": 1.5311025619506835, "lr": 1.0719514199022473e-06, "epoch": 0.8588957055214724, "percentage": 85.89, "elapsed_time": "0:37:06", "remaining_time": "0:06:05"}
+{"current_steps": 290, "total_steps": 326, "loss": 1.5679447174072265, "lr": 6.689543412899913e-07, "epoch": 0.8895705521472392, "percentage": 88.96, "elapsed_time": "0:38:26", "remaining_time": "0:04:46"}
+{"current_steps": 300, "total_steps": 326, "loss": 1.5297722816467285, "lr": 3.5810786053987025e-07, "epoch": 0.9202453987730062, "percentage": 92.02, "elapsed_time": "0:39:47", "remaining_time": "0:03:26"}
+{"current_steps": 310, "total_steps": 326, "loss": 1.5922201156616211, "lr": 1.4248180391703614e-07, "epoch": 0.950920245398773, "percentage": 95.09, "elapsed_time": "0:41:08", "remaining_time": "0:02:07"}
+{"current_steps": 320, "total_steps": 326, "loss": 1.512490463256836, "lr": 2.420562944358329e-08, "epoch": 0.9815950920245399, "percentage": 98.16, "elapsed_time": "0:42:27", "remaining_time": "0:00:47"}
+{"current_steps": 326, "total_steps": 326, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:43:14", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,267 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 326,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03067484662576687,
+      "grad_norm": 8.0,
+      "learning_rate": 1.8e-05,
+      "loss": 2.659077453613281,
+      "step": 10
+    },
+    {
+      "epoch": 0.06134969325153374,
+      "grad_norm": 3.296875,
+      "learning_rate": 1.995999715857997e-05,
+      "loss": 2.113694763183594,
+      "step": 20
+    },
+    {
+      "epoch": 0.09202453987730061,
+      "grad_norm": 2.984375,
+      "learning_rate": 1.9822126571413616e-05,
+      "loss": 1.8163612365722657,
+      "step": 30
+    },
+    {
+      "epoch": 0.12269938650306748,
+      "grad_norm": 3.375,
+      "learning_rate": 1.9587255619128648e-05,
+      "loss": 1.7940385818481446,
+      "step": 40
+    },
+    {
+      "epoch": 0.15337423312883436,
+      "grad_norm": 2.90625,
+      "learning_rate": 1.9257703816543144e-05,
+      "loss": 1.702846145629883,
+      "step": 50
+    },
+    {
+      "epoch": 0.18404907975460122,
+      "grad_norm": 2.890625,
+      "learning_rate": 1.8836725718049562e-05,
+      "loss": 1.6503068923950195,
+      "step": 60
+    },
+    {
+      "epoch": 0.2147239263803681,
+      "grad_norm": 3.265625,
+      "learning_rate": 1.8328478776615336e-05,
+      "loss": 1.6176418304443358,
+      "step": 70
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "grad_norm": 3.125,
+      "learning_rate": 1.7737982286028938e-05,
+      "loss": 1.649836540222168,
+      "step": 80
+    },
+    {
+      "epoch": 0.27607361963190186,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 1.6427200317382813,
+      "step": 90
+    },
+    {
+      "epoch": 0.3067484662576687,
+      "grad_norm": 2.5625,
+      "learning_rate": 1.6334321600700612e-05,
+      "loss": 1.5673911094665527,
+      "step": 100
+    },
+    {
+      "epoch": 0.3374233128834356,
+      "grad_norm": 3.453125,
+      "learning_rate": 1.5535019536322158e-05,
+      "loss": 1.5665663719177245,
+      "step": 110
+    },
+    {
+      "epoch": 0.36809815950920244,
+      "grad_norm": 3.28125,
+      "learning_rate": 1.4681055285292138e-05,
+      "loss": 1.549239158630371,
+      "step": 120
+    },
+    {
+      "epoch": 0.3987730061349693,
+      "grad_norm": 3.015625,
+      "learning_rate": 1.3780862341472183e-05,
+      "loss": 1.5795641899108888,
+      "step": 130
+    },
+    {
+      "epoch": 0.4294478527607362,
+      "grad_norm": 2.90625,
+      "learning_rate": 1.2843330739377003e-05,
+      "loss": 1.5186445236206054,
+      "step": 140
+    },
+    {
+      "epoch": 0.4601226993865031,
+      "grad_norm": 2.890625,
+      "learning_rate": 1.1877719258869827e-05,
+      "loss": 1.5579788208007812,
+      "step": 150
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "grad_norm": 3.578125,
+      "learning_rate": 1.0893563988239773e-05,
+      "loss": 1.5645319938659668,
+      "step": 160
+    },
+    {
+      "epoch": 0.5214723926380368,
+      "grad_norm": 2.671875,
+      "learning_rate": 9.900584148664705e-06,
+      "loss": 1.5919049263000489,
+      "step": 170
+    },
+    {
+      "epoch": 0.5521472392638037,
+      "grad_norm": 2.25,
+      "learning_rate": 8.908586110108794e-06,
+      "loss": 1.571799087524414,
+      "step": 180
+    },
+    {
+      "epoch": 0.5828220858895705,
+      "grad_norm": 2.625,
+      "learning_rate": 7.927366546564911e-06,
+      "loss": 1.5389130592346192,
+      "step": 190
+    },
+    {
+      "epoch": 0.6134969325153374,
+      "grad_norm": 2.640625,
+      "learning_rate": 6.966615687051517e-06,
+      "loss": 1.5266441345214843,
+      "step": 200
+    },
+    {
+      "epoch": 0.6441717791411042,
+      "grad_norm": 3.015625,
+      "learning_rate": 6.03582161782806e-06,
+      "loss": 1.5582975387573241,
+      "step": 210
+    },
+    {
+      "epoch": 0.6748466257668712,
+      "grad_norm": 2.921875,
+      "learning_rate": 5.144176580911431e-06,
+      "loss": 1.5671936988830566,
+      "step": 220
+    },
+    {
+      "epoch": 0.7055214723926381,
+      "grad_norm": 2.4375,
+      "learning_rate": 4.3004861942610575e-06,
+      "loss": 1.5731188774108886,
+      "step": 230
+    },
+    {
+      "epoch": 0.7361963190184049,
+      "grad_norm": 3.328125,
+      "learning_rate": 3.513082490146864e-06,
+      "loss": 1.5142654418945312,
+      "step": 240
+    },
+    {
+      "epoch": 0.7668711656441718,
+      "grad_norm": 3.046875,
+      "learning_rate": 2.7897416305068325e-06,
+      "loss": 1.5008227348327636,
+      "step": 250
+    },
+    {
+      "epoch": 0.7975460122699386,
+      "grad_norm": 2.875,
+      "learning_rate": 2.137607111912734e-06,
+      "loss": 1.585028839111328,
+      "step": 260
+    },
+    {
+      "epoch": 0.8282208588957055,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.5631192185484557e-06,
+      "loss": 1.571006679534912,
+      "step": 270
+    },
+    {
+      "epoch": 0.8588957055214724,
+      "grad_norm": 3.046875,
+      "learning_rate": 1.0719514199022473e-06,
+      "loss": 1.5311025619506835,
+      "step": 280
+    },
+    {
+      "epoch": 0.8895705521472392,
+      "grad_norm": 2.78125,
+      "learning_rate": 6.689543412899913e-07,
+      "loss": 1.5679447174072265,
+      "step": 290
+    },
+    {
+      "epoch": 0.9202453987730062,
+      "grad_norm": 2.6875,
+      "learning_rate": 3.5810786053987025e-07,
+      "loss": 1.5297722816467285,
+      "step": 300
+    },
+    {
+      "epoch": 0.950920245398773,
+      "grad_norm": 2.75,
+      "learning_rate": 1.4248180391703614e-07,
+      "loss": 1.5922201156616211,
+      "step": 310
+    },
+    {
+      "epoch": 0.9815950920245399,
+      "grad_norm": 2.796875,
+      "learning_rate": 2.420562944358329e-08,
+      "loss": 1.512490463256836,
+      "step": 320
+    },
+    {
+      "epoch": 1.0,
+      "step": 326,
+      "total_flos": 1.563295846805975e+17,
+      "train_loss": 1.6355595296145948,
+      "train_runtime": 2594.717,
+      "train_samples_per_second": 0.503,
+      "train_steps_per_second": 0.126
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 326,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.563295846805975e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0659c9c09f00989397efedd01a95ea3237e1053d20ffd03ebf4163280bbd809a
+size 6033